{"task":"Math Word Problem Solving","dataset":"MATH","metric_names":["Accuracy","Parameters (Billions)"],"rows":[{"id":25211,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Gemini 2.0 Flash Experimental","metrics":{"Accuracy":"89.7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25212,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2.5-Math-72B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"88.1","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25213,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4 Turbo (MACM, w/code, voting)","metrics":{"Accuracy":"87.920"},"paper_url":"https://arxiv.org/abs/2404.04735v2","paper_title":"MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems","paper_date":"2024-04-06","code_links":[{"title":"bin123apple/macm","url":"https://github.com/bin123apple/macm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25214,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2.5-Math-72B-Instruct(COT,Greedy)","metrics":{"Accuracy":"85.9","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25215,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2.5-Math-7B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"85.2","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25216,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4-code model (CSV, w/ code, SC, k=16)","metrics":{"Accuracy":"84.3"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25217,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2-Math-72B-Instruct(greedy)","metrics":{"Accuracy":"84.0","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2407.10671v4","paper_title":"Qwen2 Technical Report","paper_date":"2024-07-15","code_links":[{"title":"qwenlm/qwen1.5","url":"https://github.com/qwenlm/qwen1.5"},{"title":"qwenlm/qwen2","url":"https://github.com/qwenlm/qwen2"},{"title":"vicentvankor/sun-shine","url":"https://github.com/vicentvankor/sun-shine"},{"title":"ziye2chen/LLMs-for-Mathematical-Analysis","url":"https://github.com/ziye2chen/LLMs-for-Mathematical-Analysis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/qwen2_moe"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/qwen2"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25218,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2.5-Math-7B-Instruct(COT,Greedy)","metrics":{"Accuracy":"83.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25219,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2.5-Math-1.5B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"79.9","Parameters (Billions)":"1.5"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25220,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath2-Llama3.1-70B (majority@256)","metrics":{"Accuracy":"79.6"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25221,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath2-Llama3.1-8B (majority@256)","metrics":{"Accuracy":"76.1"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25222,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2.5-Math-1.5B-Instruct(COT,Greedy)","metrics":{"Accuracy":"75.8","Parameters (Billions)":"1.5"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25223,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4-code model (CSV, w/ code)","metrics":{"Accuracy":"73.5"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25224,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"CR (GPT-4-turbo model, w/ code)","metrics":{"Accuracy":"72.2"},"paper_url":"https://arxiv.org/abs/2308.04371v6","paper_title":"Cumulative Reasoning with Large Language Models","paper_date":"2023-08-08","code_links":[{"title":"iiis-ai/cumulative-reasoning","url":"https://github.com/iiis-ai/cumulative-reasoning"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25225,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath2-Llama3.1-70B","metrics":{"Accuracy":"71.9"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25226,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LogicNet (with code interpreter)","metrics":{"Accuracy":"71.2"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25227,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2-72B-Instruct-Step-DPO (0-shot CoT, w/o code)","metrics":{"Accuracy":"70.8"},"paper_url":"https://arxiv.org/abs/2406.18629v1","paper_title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","paper_date":"2024-06-26","code_links":[{"title":"dvlab-research/step-dpo","url":"https://github.com/dvlab-research/step-dpo"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25228,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4-code model (w/ code)","metrics":{"Accuracy":"69.7"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25229,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath2-Llama3.1-8B","metrics":{"Accuracy":"67.8"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25230,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"AlphaMath-7B-SBS@3","metrics":{"Accuracy":"66.3"},"paper_url":"https://arxiv.org/abs/2405.03553v3","paper_title":"AlphaMath Almost Zero: Process Supervision without Process","paper_date":"2024-05-06","code_links":[{"title":"MARIO-Math-Reasoning/Super_MARIO","url":"https://github.com/MARIO-Math-Reasoning/Super_MARIO"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25231,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 62B (maj5@256)","metrics":{"Accuracy":"64.9","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25232,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DAMOMath-7B","metrics":{"Accuracy":"64.5","Parameters (Billions)":"7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25233,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MMOS-DeepSeekMath-7B(0-shot,k=50)","metrics":{"Accuracy":"63.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25234,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4-code model (w/o code)","metrics":{"Accuracy":"60.8"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25235,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-70B (w/ code, SC, k=50)","metrics":{"Accuracy":"60.4","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25236,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-34B (w/ code, SC, k=50)","metrics":{"Accuracy":"60.2","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25237,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA-Code 34B model (w/ code, SC, k=50)","metrics":{"Accuracy":"60.0","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25238,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DeepSeekMATH-RL-7B (w/ code, greedy decoding)","metrics":{"Accuracy":"58.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.03300v3","paper_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","paper_date":"2024-02-05","code_links":[{"title":"shibing624/medicalgpt","url":"https://github.com/shibing624/medicalgpt"},{"title":"deepseek-ai/deepseek-math","url":"https://github.com/deepseek-ai/deepseek-math"},{"title":"openpsi-project/realhf","url":"https://github.com/openpsi-project/realhf"},{"title":"synthlabsai/big-math","url":"https://github.com/synthlabsai/big-math"},{"title":"yynil/rwkvinside","url":"https://github.com/yynil/rwkvinside"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25239,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-Llama2-70B (w/ code, SC, k=50)","metrics":{"Accuracy":"58.3","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25240,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"CR (GPT-4 model, w/o code)","metrics":{"Accuracy":"58.0"},"paper_url":"https://arxiv.org/abs/2308.04371v6","paper_title":"Cumulative Reasoning with Large Language Models","paper_date":"2023-08-08","code_links":[{"title":"iiis-ai/cumulative-reasoning","url":"https://github.com/iiis-ai/cumulative-reasoning"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25241,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-13B (w/ code, SC, k=50)","metrics":{"Accuracy":"57.6","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25242,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-Mistral-7B (w/ code, SC, k=50)","metrics":{"Accuracy":"57.2","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25243,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA 70B (w/ code, SC, k=50)","metrics":{"Accuracy":"56.9","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25244,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"SKiC (GPT-4 model)","metrics":{"Accuracy":"56.4"},"paper_url":"https://arxiv.org/abs/2308.00304v3","paper_title":"Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models","paper_date":"2023-08-01","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25245,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-Llama3-70B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"56.1","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25246,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-7B (w/ code, SC, k=50)","metrics":{"Accuracy":"55.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25247,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MMOS-DeepSeekMath-7B(0-shot)","metrics":{"Accuracy":"55.0","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25248,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-Llama3-70B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"54.9","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25249,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PHP (GPT-4 model)","metrics":{"Accuracy":"53.9"},"paper_url":"https://arxiv.org/abs/2304.09797v6","paper_title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","paper_date":"2023-04-19","code_links":[{"title":"chuanyang-Zheng/Progressive-Hint","url":"https://github.com/chuanyang-Zheng/Progressive-Hint"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25250,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-DSMath-7B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"53.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25251,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Gemini Ultra (4-shot)","metrics":{"Accuracy":"53.2"},"paper_url":"https://arxiv.org/abs/2312.11805v5","paper_title":"Gemini: A Family of Highly Capable Multimodal Models","paper_date":"2023-12-19","code_links":[{"title":"valdecy/pybibx","url":"https://github.com/valdecy/pybibx"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25252,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-DSMath-7B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"52.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25253,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4 model (w/ code, PAL)","metrics":{"Accuracy":"51.8"},"paper_url":"https://arxiv.org/abs/2211.10435v2","paper_title":"PAL: Program-aided Language Models","paper_date":"2022-11-18","code_links":[{"title":"srush/minichain","url":"https://github.com/srush/minichain"},{"title":"RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox"},{"title":"allanj/dynamic-pal","url":"https://github.com/allanj/dynamic-pal"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25254,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DeepSeekMATH-RL-7B (greedy decoding)","metrics":{"Accuracy":"51.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.03300v3","paper_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","paper_date":"2024-02-05","code_links":[{"title":"shibing624/medicalgpt","url":"https://github.com/shibing624/medicalgpt"},{"title":"deepseek-ai/deepseek-math","url":"https://github.com/deepseek-ai/deepseek-math"},{"title":"openpsi-project/realhf","url":"https://github.com/openpsi-project/realhf"},{"title":"synthlabsai/big-math","url":"https://github.com/synthlabsai/big-math"},{"title":"yynil/rwkvinside","url":"https://github.com/yynil/rwkvinside"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25255,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"AlphaLLM (with MCTS)","metrics":{"Accuracy":"51"},"paper_url":"https://arxiv.org/abs/2404.12253v2","paper_title":"Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing","paper_date":"2024-04-18","code_links":[{"title":"yetianjhu/alphallm","url":"https://github.com/yetianjhu/alphallm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25256,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA-Code 34B (w/ code)","metrics":{"Accuracy":"50.8","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25257,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Accuracy":"50.7","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25258,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 540B (maj1@k, k=64)","metrics":{"Accuracy":"50.3"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25259,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA 70B (w/ code)","metrics":{"Accuracy":"49.7","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25260,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MMOS-CODE-34B(0-shot)","metrics":{"Accuracy":"49.5","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25261,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DeepSeekMath-7B-KPMath-Plus","metrics":{"Accuracy":"48.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25262,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 2 (few-shot, k=4, SC)","metrics":{"Accuracy":"48.8"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25263,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Llemma-34B-KPMath-Plus","metrics":{"Accuracy":"48.6","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25264,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-34B (w/ code)","metrics":{"Accuracy":"48.3","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25265,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Shepherd + DeepSeek-67B (SFT on MetaMATH + PRM rerank, k=256)","metrics":{"Accuracy":"48.1","Parameters (Billions)":"67"},"paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","paper_date":"2023-12-14","code_links":[{"title":"hkust-nlp/b-star","url":"https://github.com/hkust-nlp/b-star"},{"title":"chang-github-00/llm-predictive-decoding","url":"https://github.com/chang-github-00/llm-predictive-decoding"},{"title":"peiyi9979/Math-Shepherd","url":"https://huggingface.co/datasets/peiyi9979/Math-Shepherd"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25266,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA-Code 13B (w/ code)","metrics":{"Accuracy":"48.1","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25267,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 8B (maj5@256)","metrics":{"Accuracy":"47.6","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25268,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Mistral-7B-KPMath-Plus","metrics":{"Accuracy":"46.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25269,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-Llama3-8B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"46.6","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25270,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-Llama2-70B (w/ code)","metrics":{"Accuracy":"46.3","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25271,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-13B (w/ code)","metrics":{"Accuracy":"45.5","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25272,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-Mistral-7B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"45.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25273,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-Llama3-8B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"45.3","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25274,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MathCoder-CL-34B","metrics":{"Accuracy":"45.2","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25275,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MathCoder-L-34B","metrics":{"Accuracy":"45.1","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25276,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MMIQC-72B","metrics":{"Accuracy":"45.0","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2401.09003v5","paper_title":"Augmenting Math Word Problems via Iterative Question Composing","paper_date":"2024-01-17","code_links":[{"title":"iiis-ai/iterativequestioncomposing","url":"https://github.com/iiis-ai/iterativequestioncomposing"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25277,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA-Code 7B (w/ code)","metrics":{"Accuracy":"44.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25278,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-Mistral-7B (w/ code)","metrics":{"Accuracy":"44.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25279,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MMOS-CODE-7B(0-shot)","metrics":{"Accuracy":"44.3","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25280,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-7B (w/ code)","metrics":{"Accuracy":"43.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25281,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Shepherd+Mistral-7B (SFT on MetaMATH + PRM RL+ PRM rerank, k=256)","metrics":{"Accuracy":"43.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","paper_date":"2023-12-14","code_links":[{"title":"hkust-nlp/b-star","url":"https://github.com/hkust-nlp/b-star"},{"title":"chang-github-00/llm-predictive-decoding","url":"https://github.com/chang-github-00/llm-predictive-decoding"},{"title":"peiyi9979/Math-Shepherd","url":"https://huggingface.co/datasets/peiyi9979/Math-Shepherd"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25282,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-Mistral-7B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"43.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25283,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 62B (maj1@k, k=64)","metrics":{"Accuracy":"43.4","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25284,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA 13B (w/ code)","metrics":{"Accuracy":"43.0","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25285,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4","metrics":{"Accuracy":"42.5"},"paper_url":"https://arxiv.org/abs/2303.12712v5","paper_title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","paper_date":"2023-03-22","code_links":[{"title":"microsoft/guidance","url":"https://github.com/microsoft/guidance"},{"title":"gammatauai/leetcode-hard-gym","url":"https://github.com/gammatauai/leetcode-hard-gym"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25286,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"SFT-Mistral-7B","metrics":{"Accuracy":"41.8","Parameters (Billions)":"7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25287,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Llama2-13B-KPMath-Plus","metrics":{"Accuracy":"41","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25288,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA 7B (w/ code)","metrics":{"Accuracy":"40.1","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25289,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MathCoder-CL-13B","metrics":{"Accuracy":"35.9","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25290,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MuggleMATH-70B","metrics":{"Accuracy":"35.6","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","paper_date":"2023-10-09","code_links":[{"title":"ofa-sys/gsm8k-screl","url":"https://github.com/ofa-sys/gsm8k-screl"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25291,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 2 (few-shot, k=4, CoT)","metrics":{"Accuracy":"34.3"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25292,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 540B","metrics":{"Accuracy":"33.6","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25293,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 540B (5-shot) mCoT","metrics":{"Accuracy":"33.6","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25294,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Shepherd + Mistral-7B (SFT on MetaMATH + PRM RL)","metrics":{"Accuracy":"33.0","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","paper_date":"2023-12-14","code_links":[{"title":"hkust-nlp/b-star","url":"https://github.com/hkust-nlp/b-star"},{"title":"chang-github-00/llm-predictive-decoding","url":"https://github.com/chang-github-00/llm-predictive-decoding"},{"title":"peiyi9979/Math-Shepherd","url":"https://huggingface.co/datasets/peiyi9979/Math-Shepherd"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25295,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"WizardMath-7B-V1.1","metrics":{"Accuracy":"33.0","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25296,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Gemini Pro (4-shot)","metrics":{"Accuracy":"32.6"},"paper_url":"https://arxiv.org/abs/2312.11805v5","paper_title":"Gemini: A Family of Highly Capable Multimodal Models","paper_date":"2023-12-19","code_links":[{"title":"valdecy/pybibx","url":"https://github.com/valdecy/pybibx"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25297,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MuggleMATH-13B","metrics":{"Accuracy":"30.7","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","paper_date":"2023-10-09","code_links":[{"title":"ofa-sys/gsm8k-screl","url":"https://github.com/ofa-sys/gsm8k-screl"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25298,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MathCoder-CL-7B","metrics":{"Accuracy":"30.2","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25299,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MathCoder-L-13B","metrics":{"Accuracy":"29.9","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25300,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2idae-16x14B (4-shot)","metrics":{"Accuracy":"29.9"},"paper_url":"https://arxiv.org/abs/2401.02731v4","paper_title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","paper_date":"2024-01-05","code_links":[{"title":"wuhy68/parameter-efficient-moe","url":"https://github.com/wuhy68/parameter-efficient-moe"},{"title":"ShayekhBinIslam/openrag","url":"https://github.com/ShayekhBinIslam/openrag"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25301,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenChat-3.5-1210 7B","metrics":{"Accuracy":"28.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.11235v2","paper_title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","paper_date":"2023-09-20","code_links":[{"title":"imoneoi/openchat","url":"https://github.com/imoneoi/openchat"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25302,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenChat-3.5 7B","metrics":{"Accuracy":"28.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.11235v2","paper_title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","paper_date":"2023-09-20","code_links":[{"title":"imoneoi/openchat","url":"https://github.com/imoneoi/openchat"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25303,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Mixtral 8x7B (maj@4)","metrics":{"Accuracy":"28.4"},"paper_url":"https://arxiv.org/abs/2401.04088v1","paper_title":"Mixtral of Experts","paper_date":"2024-01-08","code_links":[{"title":"jingyaogong/minimind","url":"https://github.com/jingyaogong/minimind"},{"title":"hit-scir/chinese-mixtral-8x7b","url":"https://github.com/hit-scir/chinese-mixtral-8x7b"},{"title":"ymcui/chinese-mixtral","url":"https://github.com/ymcui/chinese-mixtral"},{"title":"consequentai/fneval","url":"https://github.com/consequentai/fneval"},{"title":"kamanphoebe/look-into-moes","url":"https://github.com/kamanphoebe/look-into-moes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mixtral"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25304,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 62B (4-shot)","metrics":{"Accuracy":"27.6","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25305,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MetaMath 70B","metrics":{"Accuracy":"26.0","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","paper_date":"2023-09-21","code_links":[{"title":"meta-math/MetaMath","url":"https://github.com/meta-math/MetaMath"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25306,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MuggleMATH 7B","metrics":{"Accuracy":"25.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","paper_date":"2023-10-09","code_links":[{"title":"ofa-sys/gsm8k-screl","url":"https://github.com/ofa-sys/gsm8k-screl"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25307,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 8B (maj1@k, k=64)","metrics":{"Accuracy":"25.4","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25308,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MathCoder-L-7B","metrics":{"Accuracy":"23.3","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25309,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"WizardMath-70B-V1.0","metrics":{"Accuracy":"22.7","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25310,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Camelidae-8×34B (4-shot)","metrics":{"Accuracy":"22.6"},"paper_url":"https://arxiv.org/abs/2401.02731v4","paper_title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","paper_date":"2024-01-05","code_links":[{"title":"wuhy68/parameter-efficient-moe","url":"https://github.com/wuhy68/parameter-efficient-moe"},{"title":"ShayekhBinIslam/openrag","url":"https://github.com/ShayekhBinIslam/openrag"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25311,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MetaMath 13B","metrics":{"Accuracy":"22.5","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","paper_date":"2023-09-21","code_links":[{"title":"meta-math/MetaMath","url":"https://github.com/meta-math/MetaMath"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25312,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 65B (maj1@k)","metrics":{"Accuracy":"20.5","Parameters (Billions)":"65"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25313,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GAL 120B (5-shot) mCoT","metrics":{"Accuracy":"20.4","Parameters (Billions)":"120"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25314,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MetaMath 7B","metrics":{"Accuracy":"19.4","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","paper_date":"2023-09-21","code_links":[{"title":"meta-math/MetaMath","url":"https://github.com/meta-math/MetaMath"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25315,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"davinci-002 175B","metrics":{"Accuracy":"19.1","Parameters (Billions)":"175"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25316,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Branch-Train-MiX 4x7B (sampling top-2 experts)","metrics":{"Accuracy":"17.8"},"paper_url":"https://arxiv.org/abs/2403.07816v1","paper_title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","paper_date":"2024-03-12","code_links":[{"title":"Leeroo-AI/mergoo","url":"https://github.com/Leeroo-AI/mergoo"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25317,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GAL 120B <work>","metrics":{"Accuracy":"16.6","Parameters (Billions)":"120"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25318,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 33B-maj1@k","metrics":{"Accuracy":"15.2","Parameters (Billions)":"33"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25319,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 8B","metrics":{"Accuracy":"14.1","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25320,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"WizardMath-13B-V1.0","metrics":{"Accuracy":"14.0","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25321,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Mistral 7B (maj@4)","metrics":{"Accuracy":"13.1","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.06825v1","paper_title":"Mistral 7B","paper_date":"2023-10-10","code_links":[{"title":"mistralai/mistral-src","url":"https://github.com/mistralai/mistral-src"},{"title":"facebookresearch/fairseq2","url":"https://github.com/facebookresearch/fairseq2"},{"title":"mgmalek/efficient_cross_entropy","url":"https://github.com/mgmalek/efficient_cross_entropy"},{"title":"ninglab/ecellm","url":"https://github.com/ninglab/ecellm"},{"title":"knowlab/bi-weekly-paper-presentation","url":"https://github.com/knowlab/bi-weekly-paper-presentation"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mistral"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25322,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GAL 30B (5-shot) mCoT","metrics":{"Accuracy":"12.7","Parameters (Billions)":"30"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25323,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Mistral 7B (maj@4)","metrics":{"Accuracy":"12.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2401.04088v1","paper_title":"Mixtral of Experts","paper_date":"2024-01-08","code_links":[{"title":"jingyaogong/minimind","url":"https://github.com/jingyaogong/minimind"},{"title":"hit-scir/chinese-mixtral-8x7b","url":"https://github.com/hit-scir/chinese-mixtral-8x7b"},{"title":"ymcui/chinese-mixtral","url":"https://github.com/ymcui/chinese-mixtral"},{"title":"consequentai/fneval","url":"https://github.com/consequentai/fneval"},{"title":"kamanphoebe/look-into-moes","url":"https://github.com/kamanphoebe/look-into-moes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mixtral"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25324,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GAL 30B <work>","metrics":{"Accuracy":"11.4","Parameters (Billions)":"30"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25325,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"WizardMath-7B-V1.0","metrics":{"Accuracy":"10.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25326,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 65B","metrics":{"Accuracy":"10.6","Parameters (Billions)":"65"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25327,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 540B","metrics":{"Accuracy":"8.8","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25328,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 540B (5-shot) mCoT","metrics":{"Accuracy":"8.8","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25329,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 13B-maj1@k","metrics":{"Accuracy":"8.8","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25330,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 33B","metrics":{"Accuracy":"7.1","Parameters (Billions)":"33"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25331,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 7B-maj1@k","metrics":{"Accuracy":"6.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25332,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-2 (1.5B)","metrics":{"Accuracy":"6.9","Parameters (Billions)":"1.5"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25333,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-2 (0.7B)","metrics":{"Accuracy":"6.4","Parameters (Billions)":"0.7"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25334,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-2 (0.3B)","metrics":{"Accuracy":"6.2","Parameters (Billions)":"0.3"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25335,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-3 13B","metrics":{"Accuracy":"5.6","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25336,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 8B (fine-tuned)","metrics":{"Accuracy":"5.6","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25337,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-2 (0.1B)","metrics":{"Accuracy":"5.4","Parameters (Billions)":"0.1"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25338,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-3-175B (few-shot)","metrics":{"Accuracy":"5.2","Parameters (Billions)":"175"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25339,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-3 175B (8-shot)","metrics":{"Accuracy":"5.2","Parameters (Billions)":"175"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25340,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 62B","metrics":{"Accuracy":"4.4","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25341,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 13B","metrics":{"Accuracy":"3.9","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25342,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-3-13B (few-shot)","metrics":{"Accuracy":"3.0","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25343,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 7B","metrics":{"Accuracy":"2.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25344,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-3 2.7B","metrics":{"Accuracy":"2.9","Parameters (Billions)":"2.7"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25345,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 8B","metrics":{"Accuracy":"1.5","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94789,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Gemini 2.0 Flash Experimental","metrics":{"Accuracy":"89.7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94790,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Qwen2.5-Math-72B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"88.1","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94791,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-4 Turbo (MACM, w/code, voting)","metrics":{"Accuracy":"87.920"},"paper_url":"https://arxiv.org/abs/2404.04735v2","paper_title":"MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems","paper_date":"2024-04-06","code_links":[{"title":"bin123apple/macm","url":"https://github.com/bin123apple/macm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94792,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Qwen2.5-Math-72B-Instruct(COT,Greedy)","metrics":{"Accuracy":"85.9","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94793,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Qwen2.5-Math-7B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"85.2","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94794,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-4-code model (CSV, w/ code, SC, k=16)","metrics":{"Accuracy":"84.3"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94795,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Qwen2-Math-72B-Instruct(greedy)","metrics":{"Accuracy":"84.0","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2407.10671v4","paper_title":"Qwen2 Technical Report","paper_date":"2024-07-15","code_links":[{"title":"qwenlm/qwen1.5","url":"https://github.com/qwenlm/qwen1.5"},{"title":"qwenlm/qwen2","url":"https://github.com/qwenlm/qwen2"},{"title":"vicentvankor/sun-shine","url":"https://github.com/vicentvankor/sun-shine"},{"title":"ziye2chen/LLMs-for-Mathematical-Analysis","url":"https://github.com/ziye2chen/LLMs-for-Mathematical-Analysis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/qwen2_moe"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/qwen2"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94796,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Qwen2.5-Math-7B-Instruct(COT,Greedy)","metrics":{"Accuracy":"83.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94797,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Qwen2.5-Math-1.5B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"79.9","Parameters (Billions)":"1.5"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94798,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath2-Llama3.1-70B (majority@256)","metrics":{"Accuracy":"79.6"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94799,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath2-Llama3.1-8B (majority@256)","metrics":{"Accuracy":"76.1"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94800,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Qwen2.5-Math-1.5B-Instruct(COT,Greedy)","metrics":{"Accuracy":"75.8","Parameters (Billions)":"1.5"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94801,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-4-code model (CSV, w/ code)","metrics":{"Accuracy":"73.5"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94802,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"CR (GPT-4-turbo model, w/ code)","metrics":{"Accuracy":"72.2"},"paper_url":"https://arxiv.org/abs/2308.04371v6","paper_title":"Cumulative Reasoning with Large Language Models","paper_date":"2023-08-08","code_links":[{"title":"iiis-ai/cumulative-reasoning","url":"https://github.com/iiis-ai/cumulative-reasoning"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94803,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath2-Llama3.1-70B","metrics":{"Accuracy":"71.9"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94804,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"LogicNet (with code interpreter)","metrics":{"Accuracy":"71.2"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94805,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Qwen2-72B-Instruct-Step-DPO (0-shot CoT, w/o code)","metrics":{"Accuracy":"70.8"},"paper_url":"https://arxiv.org/abs/2406.18629v1","paper_title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","paper_date":"2024-06-26","code_links":[{"title":"dvlab-research/step-dpo","url":"https://github.com/dvlab-research/step-dpo"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94806,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-4-code model (w/ code)","metrics":{"Accuracy":"69.7"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94807,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath2-Llama3.1-8B","metrics":{"Accuracy":"67.8"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94808,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"AlphaMath-7B-SBS@3","metrics":{"Accuracy":"66.3"},"paper_url":"https://arxiv.org/abs/2405.03553v3","paper_title":"AlphaMath Almost Zero: Process Supervision without Process","paper_date":"2024-05-06","code_links":[{"title":"MARIO-Math-Reasoning/Super_MARIO","url":"https://github.com/MARIO-Math-Reasoning/Super_MARIO"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94809,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Minerva 62B (maj5@256)","metrics":{"Accuracy":"64.9","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94810,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"DAMOMath-7B","metrics":{"Accuracy":"64.5","Parameters (Billions)":"7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94811,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MMOS-DeepSeekMath-7B(0-shot,k=50)","metrics":{"Accuracy":"63.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94812,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-4-code model (w/o code)","metrics":{"Accuracy":"60.8"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94813,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath-CodeLlama-70B (w/ code, SC, k=50)","metrics":{"Accuracy":"60.4","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94814,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath-CodeLlama-34B (w/ code, SC, k=50)","metrics":{"Accuracy":"60.2","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94815,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"ToRA-Code 34B model (w/ code, SC, k=50)","metrics":{"Accuracy":"60.0","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94816,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"DeepSeekMATH-RL-7B (w/ code, greedy decoding)","metrics":{"Accuracy":"58.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.03300v3","paper_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","paper_date":"2024-02-05","code_links":[{"title":"shibing624/medicalgpt","url":"https://github.com/shibing624/medicalgpt"},{"title":"deepseek-ai/deepseek-math","url":"https://github.com/deepseek-ai/deepseek-math"},{"title":"openpsi-project/realhf","url":"https://github.com/openpsi-project/realhf"},{"title":"synthlabsai/big-math","url":"https://github.com/synthlabsai/big-math"},{"title":"yynil/rwkvinside","url":"https://github.com/yynil/rwkvinside"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94817,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath-Llama2-70B (w/ code, SC, k=50)","metrics":{"Accuracy":"58.3","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94818,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"CR (GPT-4 model, w/o code)","metrics":{"Accuracy":"58.0"},"paper_url":"https://arxiv.org/abs/2308.04371v6","paper_title":"Cumulative Reasoning with Large Language Models","paper_date":"2023-08-08","code_links":[{"title":"iiis-ai/cumulative-reasoning","url":"https://github.com/iiis-ai/cumulative-reasoning"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94819,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath-CodeLlama-13B (w/ code, SC, k=50)","metrics":{"Accuracy":"57.6","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94820,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath-Mistral-7B (w/ code, SC, k=50)","metrics":{"Accuracy":"57.2","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94821,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"ToRA 70B (w/ code, SC, k=50)","metrics":{"Accuracy":"56.9","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94822,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"SKiC (GPT-4 model)","metrics":{"Accuracy":"56.4"},"paper_url":"https://arxiv.org/abs/2308.00304v3","paper_title":"Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models","paper_date":"2023-08-01","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94823,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"DART-Math-Llama3-70B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"56.1","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94824,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath-CodeLlama-7B (w/ code, SC, k=50)","metrics":{"Accuracy":"55.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94825,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MMOS-DeepSeekMath-7B(0-shot)","metrics":{"Accuracy":"55.0","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94826,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"DART-Math-Llama3-70B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"54.9","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94827,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"PHP (GPT-4 model)","metrics":{"Accuracy":"53.9"},"paper_url":"https://arxiv.org/abs/2304.09797v6","paper_title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","paper_date":"2023-04-19","code_links":[{"title":"chuanyang-Zheng/Progressive-Hint","url":"https://github.com/chuanyang-Zheng/Progressive-Hint"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94828,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"DART-Math-DSMath-7B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"53.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94829,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Gemini Ultra (4-shot)","metrics":{"Accuracy":"53.2"},"paper_url":"https://arxiv.org/abs/2312.11805v5","paper_title":"Gemini: A Family of Highly Capable Multimodal Models","paper_date":"2023-12-19","code_links":[{"title":"valdecy/pybibx","url":"https://github.com/valdecy/pybibx"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94830,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"DART-Math-DSMath-7B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"52.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94831,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-4 model (w/ code, PAL)","metrics":{"Accuracy":"51.8"},"paper_url":"https://arxiv.org/abs/2211.10435v2","paper_title":"PAL: Program-aided Language Models","paper_date":"2022-11-18","code_links":[{"title":"srush/minichain","url":"https://github.com/srush/minichain"},{"title":"RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox"},{"title":"allanj/dynamic-pal","url":"https://github.com/allanj/dynamic-pal"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94832,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"DeepSeekMATH-RL-7B (greedy decoding)","metrics":{"Accuracy":"51.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.03300v3","paper_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","paper_date":"2024-02-05","code_links":[{"title":"shibing624/medicalgpt","url":"https://github.com/shibing624/medicalgpt"},{"title":"deepseek-ai/deepseek-math","url":"https://github.com/deepseek-ai/deepseek-math"},{"title":"openpsi-project/realhf","url":"https://github.com/openpsi-project/realhf"},{"title":"synthlabsai/big-math","url":"https://github.com/synthlabsai/big-math"},{"title":"yynil/rwkvinside","url":"https://github.com/yynil/rwkvinside"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94833,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"AlphaLLM (with MCTS)","metrics":{"Accuracy":"51"},"paper_url":"https://arxiv.org/abs/2404.12253v2","paper_title":"Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing","paper_date":"2024-04-18","code_links":[{"title":"yetianjhu/alphallm","url":"https://github.com/yetianjhu/alphallm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94834,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"ToRA-Code 34B (w/ code)","metrics":{"Accuracy":"50.8","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94835,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Accuracy":"50.7","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94836,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Minerva 540B (maj1@k, k=64)","metrics":{"Accuracy":"50.3"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94837,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"ToRA 70B (w/ code)","metrics":{"Accuracy":"49.7","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94838,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MMOS-CODE-34B(0-shot)","metrics":{"Accuracy":"49.5","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94839,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"DeepSeekMath-7B-KPMath-Plus","metrics":{"Accuracy":"48.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94840,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"PaLM 2 (few-shot, k=4, SC)","metrics":{"Accuracy":"48.8"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94841,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Llemma-34B-KPMath-Plus","metrics":{"Accuracy":"48.6","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94842,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath-CodeLlama-34B (w/ code)","metrics":{"Accuracy":"48.3","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94843,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Shepherd + DeepSeek-67B (SFT on MetaMATH + PRM rerank, k=256)","metrics":{"Accuracy":"48.1","Parameters (Billions)":"67"},"paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","paper_date":"2023-12-14","code_links":[{"title":"hkust-nlp/b-star","url":"https://github.com/hkust-nlp/b-star"},{"title":"chang-github-00/llm-predictive-decoding","url":"https://github.com/chang-github-00/llm-predictive-decoding"},{"title":"peiyi9979/Math-Shepherd","url":"https://huggingface.co/datasets/peiyi9979/Math-Shepherd"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94844,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"ToRA-Code 13B (w/ code)","metrics":{"Accuracy":"48.1","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94845,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Minerva 8B (maj5@256)","metrics":{"Accuracy":"47.6","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94846,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Mistral-7B-KPMath-Plus","metrics":{"Accuracy":"46.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94847,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"DART-Math-Llama3-8B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"46.6","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94848,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath-Llama2-70B (w/ code)","metrics":{"Accuracy":"46.3","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94849,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath-CodeLlama-13B (w/ code)","metrics":{"Accuracy":"45.5","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94850,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"DART-Math-Mistral-7B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"45.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94851,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"DART-Math-Llama3-8B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"45.3","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94852,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MathCoder-CL-34B","metrics":{"Accuracy":"45.2","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94853,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MathCoder-L-34B","metrics":{"Accuracy":"45.1","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94854,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MMIQC-72B","metrics":{"Accuracy":"45.0","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2401.09003v5","paper_title":"Augmenting Math Word Problems via Iterative Question Composing","paper_date":"2024-01-17","code_links":[{"title":"iiis-ai/iterativequestioncomposing","url":"https://github.com/iiis-ai/iterativequestioncomposing"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94855,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"ToRA-Code 7B (w/ code)","metrics":{"Accuracy":"44.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94856,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath-Mistral-7B (w/ code)","metrics":{"Accuracy":"44.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94857,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MMOS-CODE-7B(0-shot)","metrics":{"Accuracy":"44.3","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94858,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenMath-CodeLlama-7B (w/ code)","metrics":{"Accuracy":"43.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94859,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Shepherd+Mistral-7B (SFT on MetaMATH + PRM RL+ PRM rerank, k=256)","metrics":{"Accuracy":"43.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","paper_date":"2023-12-14","code_links":[{"title":"hkust-nlp/b-star","url":"https://github.com/hkust-nlp/b-star"},{"title":"chang-github-00/llm-predictive-decoding","url":"https://github.com/chang-github-00/llm-predictive-decoding"},{"title":"peiyi9979/Math-Shepherd","url":"https://huggingface.co/datasets/peiyi9979/Math-Shepherd"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94860,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"DART-Math-Mistral-7B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"43.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94861,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Minerva 62B (maj1@k, k=64)","metrics":{"Accuracy":"43.4","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94862,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"ToRA 13B (w/ code)","metrics":{"Accuracy":"43.0","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94863,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-4","metrics":{"Accuracy":"42.5"},"paper_url":"https://arxiv.org/abs/2303.12712v5","paper_title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","paper_date":"2023-03-22","code_links":[{"title":"microsoft/guidance","url":"https://github.com/microsoft/guidance"},{"title":"gammatauai/leetcode-hard-gym","url":"https://github.com/gammatauai/leetcode-hard-gym"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94864,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"SFT-Mistral-7B","metrics":{"Accuracy":"41.8","Parameters (Billions)":"7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94865,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Llama2-13B-KPMath-Plus","metrics":{"Accuracy":"41","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94866,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"ToRA 7B (w/ code)","metrics":{"Accuracy":"40.1","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94867,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MathCoder-CL-13B","metrics":{"Accuracy":"35.9","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94868,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MuggleMATH-70B","metrics":{"Accuracy":"35.6","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","paper_date":"2023-10-09","code_links":[{"title":"ofa-sys/gsm8k-screl","url":"https://github.com/ofa-sys/gsm8k-screl"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94869,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"PaLM 2 (few-shot, k=4, CoT)","metrics":{"Accuracy":"34.3"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94870,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Minerva 540B","metrics":{"Accuracy":"33.6","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94871,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Minerva 540B (5-shot) mCoT","metrics":{"Accuracy":"33.6","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94872,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Shepherd + Mistral-7B (SFT on MetaMATH + PRM RL)","metrics":{"Accuracy":"33.0","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","paper_date":"2023-12-14","code_links":[{"title":"hkust-nlp/b-star","url":"https://github.com/hkust-nlp/b-star"},{"title":"chang-github-00/llm-predictive-decoding","url":"https://github.com/chang-github-00/llm-predictive-decoding"},{"title":"peiyi9979/Math-Shepherd","url":"https://huggingface.co/datasets/peiyi9979/Math-Shepherd"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94873,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"WizardMath-7B-V1.1","metrics":{"Accuracy":"33.0","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94874,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Gemini Pro (4-shot)","metrics":{"Accuracy":"32.6"},"paper_url":"https://arxiv.org/abs/2312.11805v5","paper_title":"Gemini: A Family of Highly Capable Multimodal Models","paper_date":"2023-12-19","code_links":[{"title":"valdecy/pybibx","url":"https://github.com/valdecy/pybibx"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94875,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MuggleMATH-13B","metrics":{"Accuracy":"30.7","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","paper_date":"2023-10-09","code_links":[{"title":"ofa-sys/gsm8k-screl","url":"https://github.com/ofa-sys/gsm8k-screl"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94876,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MathCoder-CL-7B","metrics":{"Accuracy":"30.2","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94877,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MathCoder-L-13B","metrics":{"Accuracy":"29.9","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94878,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Qwen2idae-16x14B (4-shot)","metrics":{"Accuracy":"29.9"},"paper_url":"https://arxiv.org/abs/2401.02731v4","paper_title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","paper_date":"2024-01-05","code_links":[{"title":"wuhy68/parameter-efficient-moe","url":"https://github.com/wuhy68/parameter-efficient-moe"},{"title":"ShayekhBinIslam/openrag","url":"https://github.com/ShayekhBinIslam/openrag"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94879,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenChat-3.5-1210 7B","metrics":{"Accuracy":"28.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.11235v2","paper_title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","paper_date":"2023-09-20","code_links":[{"title":"imoneoi/openchat","url":"https://github.com/imoneoi/openchat"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94880,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"OpenChat-3.5 7B","metrics":{"Accuracy":"28.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.11235v2","paper_title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","paper_date":"2023-09-20","code_links":[{"title":"imoneoi/openchat","url":"https://github.com/imoneoi/openchat"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94881,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Mixtral 8x7B (maj@4)","metrics":{"Accuracy":"28.4"},"paper_url":"https://arxiv.org/abs/2401.04088v1","paper_title":"Mixtral of Experts","paper_date":"2024-01-08","code_links":[{"title":"jingyaogong/minimind","url":"https://github.com/jingyaogong/minimind"},{"title":"hit-scir/chinese-mixtral-8x7b","url":"https://github.com/hit-scir/chinese-mixtral-8x7b"},{"title":"ymcui/chinese-mixtral","url":"https://github.com/ymcui/chinese-mixtral"},{"title":"consequentai/fneval","url":"https://github.com/consequentai/fneval"},{"title":"kamanphoebe/look-into-moes","url":"https://github.com/kamanphoebe/look-into-moes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mixtral"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94882,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Minerva 62B (4-shot)","metrics":{"Accuracy":"27.6","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94883,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MetaMath 70B","metrics":{"Accuracy":"26.0","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","paper_date":"2023-09-21","code_links":[{"title":"meta-math/MetaMath","url":"https://github.com/meta-math/MetaMath"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94884,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MuggleMATH 7B","metrics":{"Accuracy":"25.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","paper_date":"2023-10-09","code_links":[{"title":"ofa-sys/gsm8k-screl","url":"https://github.com/ofa-sys/gsm8k-screl"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94885,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Minerva 8B (maj1@k, k=64)","metrics":{"Accuracy":"25.4","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94886,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MathCoder-L-7B","metrics":{"Accuracy":"23.3","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94887,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"WizardMath-70B-V1.0","metrics":{"Accuracy":"22.7","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94888,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Camelidae-8×34B (4-shot)","metrics":{"Accuracy":"22.6"},"paper_url":"https://arxiv.org/abs/2401.02731v4","paper_title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","paper_date":"2024-01-05","code_links":[{"title":"wuhy68/parameter-efficient-moe","url":"https://github.com/wuhy68/parameter-efficient-moe"},{"title":"ShayekhBinIslam/openrag","url":"https://github.com/ShayekhBinIslam/openrag"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94889,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MetaMath 13B","metrics":{"Accuracy":"22.5","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","paper_date":"2023-09-21","code_links":[{"title":"meta-math/MetaMath","url":"https://github.com/meta-math/MetaMath"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94890,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"LLaMA 65B (maj1@k)","metrics":{"Accuracy":"20.5","Parameters (Billions)":"65"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94891,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GAL 120B (5-shot) mCoT","metrics":{"Accuracy":"20.4","Parameters (Billions)":"120"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94892,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"MetaMath 7B","metrics":{"Accuracy":"19.4","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","paper_date":"2023-09-21","code_links":[{"title":"meta-math/MetaMath","url":"https://github.com/meta-math/MetaMath"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94893,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"davinci-002 175B","metrics":{"Accuracy":"19.1","Parameters (Billions)":"175"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94894,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Branch-Train-MiX 4x7B (sampling top-2 experts)","metrics":{"Accuracy":"17.8"},"paper_url":"https://arxiv.org/abs/2403.07816v1","paper_title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","paper_date":"2024-03-12","code_links":[{"title":"Leeroo-AI/mergoo","url":"https://github.com/Leeroo-AI/mergoo"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94895,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GAL 120B <work>","metrics":{"Accuracy":"16.6","Parameters (Billions)":"120"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94896,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"LLaMA 33B-maj1@k","metrics":{"Accuracy":"15.2","Parameters (Billions)":"33"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94897,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Minerva 8B","metrics":{"Accuracy":"14.1","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94898,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"WizardMath-13B-V1.0","metrics":{"Accuracy":"14.0","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94899,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Mistral 7B (maj@4)","metrics":{"Accuracy":"13.1","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.06825v1","paper_title":"Mistral 7B","paper_date":"2023-10-10","code_links":[{"title":"mistralai/mistral-src","url":"https://github.com/mistralai/mistral-src"},{"title":"facebookresearch/fairseq2","url":"https://github.com/facebookresearch/fairseq2"},{"title":"mgmalek/efficient_cross_entropy","url":"https://github.com/mgmalek/efficient_cross_entropy"},{"title":"ninglab/ecellm","url":"https://github.com/ninglab/ecellm"},{"title":"knowlab/bi-weekly-paper-presentation","url":"https://github.com/knowlab/bi-weekly-paper-presentation"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mistral"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94900,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GAL 30B (5-shot) mCoT","metrics":{"Accuracy":"12.7","Parameters (Billions)":"30"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94901,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"Mistral 7B (maj@4)","metrics":{"Accuracy":"12.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2401.04088v1","paper_title":"Mixtral of Experts","paper_date":"2024-01-08","code_links":[{"title":"jingyaogong/minimind","url":"https://github.com/jingyaogong/minimind"},{"title":"hit-scir/chinese-mixtral-8x7b","url":"https://github.com/hit-scir/chinese-mixtral-8x7b"},{"title":"ymcui/chinese-mixtral","url":"https://github.com/ymcui/chinese-mixtral"},{"title":"consequentai/fneval","url":"https://github.com/consequentai/fneval"},{"title":"kamanphoebe/look-into-moes","url":"https://github.com/kamanphoebe/look-into-moes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mixtral"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94902,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GAL 30B <work>","metrics":{"Accuracy":"11.4","Parameters (Billions)":"30"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94903,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"WizardMath-7B-V1.0","metrics":{"Accuracy":"10.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94904,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"LLaMA 65B","metrics":{"Accuracy":"10.6","Parameters (Billions)":"65"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94905,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"PaLM 540B","metrics":{"Accuracy":"8.8","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94906,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"PaLM 540B (5-shot) mCoT","metrics":{"Accuracy":"8.8","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94907,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"LLaMA 13B-maj1@k","metrics":{"Accuracy":"8.8","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94908,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"LLaMA 33B","metrics":{"Accuracy":"7.1","Parameters (Billions)":"33"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94909,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"LLaMA 7B-maj1@k","metrics":{"Accuracy":"6.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94910,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-2 (1.5B)","metrics":{"Accuracy":"6.9","Parameters (Billions)":"1.5"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94911,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-2 (0.7B)","metrics":{"Accuracy":"6.4","Parameters (Billions)":"0.7"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94912,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-2 (0.3B)","metrics":{"Accuracy":"6.2","Parameters (Billions)":"0.3"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94913,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-3 13B","metrics":{"Accuracy":"5.6","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94914,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"PaLM 8B (fine-tuned)","metrics":{"Accuracy":"5.6","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94915,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-2 (0.1B)","metrics":{"Accuracy":"5.4","Parameters (Billions)":"0.1"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94916,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-3-175B (few-shot)","metrics":{"Accuracy":"5.2","Parameters (Billions)":"175"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94917,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-3 175B (8-shot)","metrics":{"Accuracy":"5.2","Parameters (Billions)":"175"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94918,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"PaLM 62B","metrics":{"Accuracy":"4.4","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94919,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"LLaMA 13B","metrics":{"Accuracy":"3.9","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94920,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-3-13B (few-shot)","metrics":{"Accuracy":"3.0","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94921,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"LLaMA 7B","metrics":{"Accuracy":"2.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94922,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"GPT-3 2.7B","metrics":{"Accuracy":"2.9","Parameters (Billions)":"2.7"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94923,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MATH","model_name":"PaLM 8B","metrics":{"Accuracy":"1.5","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112035,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Gemini 2.0 Flash Experimental","metrics":{"Accuracy":"89.7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112036,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2.5-Math-72B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"88.1","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112037,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4 Turbo (MACM, w/code, voting)","metrics":{"Accuracy":"87.920"},"paper_url":"https://arxiv.org/abs/2404.04735v2","paper_title":"MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems","paper_date":"2024-04-06","code_links":[{"title":"bin123apple/macm","url":"https://github.com/bin123apple/macm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112038,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2.5-Math-72B-Instruct(COT,Greedy)","metrics":{"Accuracy":"85.9","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112039,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2.5-Math-7B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"85.2","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112040,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4-code model (CSV, w/ code, SC, k=16)","metrics":{"Accuracy":"84.3"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112041,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2-Math-72B-Instruct(greedy)","metrics":{"Accuracy":"84.0","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2407.10671v4","paper_title":"Qwen2 Technical Report","paper_date":"2024-07-15","code_links":[{"title":"qwenlm/qwen1.5","url":"https://github.com/qwenlm/qwen1.5"},{"title":"qwenlm/qwen2","url":"https://github.com/qwenlm/qwen2"},{"title":"vicentvankor/sun-shine","url":"https://github.com/vicentvankor/sun-shine"},{"title":"ziye2chen/LLMs-for-Mathematical-Analysis","url":"https://github.com/ziye2chen/LLMs-for-Mathematical-Analysis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/qwen2_moe"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/qwen2"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112042,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2.5-Math-7B-Instruct(COT,Greedy)","metrics":{"Accuracy":"83.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112043,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2.5-Math-1.5B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"79.9","Parameters (Billions)":"1.5"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112044,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath2-Llama3.1-70B (majority@256)","metrics":{"Accuracy":"79.6"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112045,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath2-Llama3.1-8B (majority@256)","metrics":{"Accuracy":"76.1"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112046,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2.5-Math-1.5B-Instruct(COT,Greedy)","metrics":{"Accuracy":"75.8","Parameters (Billions)":"1.5"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112047,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4-code model (CSV, w/ code)","metrics":{"Accuracy":"73.5"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112048,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"CR (GPT-4-turbo model, w/ code)","metrics":{"Accuracy":"72.2"},"paper_url":"https://arxiv.org/abs/2308.04371v6","paper_title":"Cumulative Reasoning with Large Language Models","paper_date":"2023-08-08","code_links":[{"title":"iiis-ai/cumulative-reasoning","url":"https://github.com/iiis-ai/cumulative-reasoning"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112049,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath2-Llama3.1-70B","metrics":{"Accuracy":"71.9"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112050,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LogicNet (with code interpreter)","metrics":{"Accuracy":"71.2"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112051,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2-72B-Instruct-Step-DPO (0-shot CoT, w/o code)","metrics":{"Accuracy":"70.8"},"paper_url":"https://arxiv.org/abs/2406.18629v1","paper_title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","paper_date":"2024-06-26","code_links":[{"title":"dvlab-research/step-dpo","url":"https://github.com/dvlab-research/step-dpo"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112052,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4-code model (w/ code)","metrics":{"Accuracy":"69.7"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112053,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath2-Llama3.1-8B","metrics":{"Accuracy":"67.8"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112054,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"AlphaMath-7B-SBS@3","metrics":{"Accuracy":"66.3"},"paper_url":"https://arxiv.org/abs/2405.03553v3","paper_title":"AlphaMath Almost Zero: Process Supervision without Process","paper_date":"2024-05-06","code_links":[{"title":"MARIO-Math-Reasoning/Super_MARIO","url":"https://github.com/MARIO-Math-Reasoning/Super_MARIO"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112055,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 62B (maj5@256)","metrics":{"Accuracy":"64.9","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112056,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DAMOMath-7B","metrics":{"Accuracy":"64.5","Parameters (Billions)":"7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112057,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MMOS-DeepSeekMath-7B(0-shot,k=50)","metrics":{"Accuracy":"63.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112058,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4-code model (w/o code)","metrics":{"Accuracy":"60.8"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112059,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-70B (w/ code, SC, k=50)","metrics":{"Accuracy":"60.4","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112060,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-34B (w/ code, SC, k=50)","metrics":{"Accuracy":"60.2","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112061,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA-Code 34B model (w/ code, SC, k=50)","metrics":{"Accuracy":"60.0","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112062,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DeepSeekMATH-RL-7B (w/ code, greedy decoding)","metrics":{"Accuracy":"58.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.03300v3","paper_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","paper_date":"2024-02-05","code_links":[{"title":"shibing624/medicalgpt","url":"https://github.com/shibing624/medicalgpt"},{"title":"deepseek-ai/deepseek-math","url":"https://github.com/deepseek-ai/deepseek-math"},{"title":"openpsi-project/realhf","url":"https://github.com/openpsi-project/realhf"},{"title":"synthlabsai/big-math","url":"https://github.com/synthlabsai/big-math"},{"title":"yynil/rwkvinside","url":"https://github.com/yynil/rwkvinside"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112063,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-Llama2-70B (w/ code, SC, k=50)","metrics":{"Accuracy":"58.3","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112064,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"CR (GPT-4 model, w/o code)","metrics":{"Accuracy":"58.0"},"paper_url":"https://arxiv.org/abs/2308.04371v6","paper_title":"Cumulative Reasoning with Large Language Models","paper_date":"2023-08-08","code_links":[{"title":"iiis-ai/cumulative-reasoning","url":"https://github.com/iiis-ai/cumulative-reasoning"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112065,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-13B (w/ code, SC, k=50)","metrics":{"Accuracy":"57.6","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112066,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-Mistral-7B (w/ code, SC, k=50)","metrics":{"Accuracy":"57.2","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112067,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA 70B (w/ code, SC, k=50)","metrics":{"Accuracy":"56.9","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112068,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"SKiC (GPT-4 model)","metrics":{"Accuracy":"56.4"},"paper_url":"https://arxiv.org/abs/2308.00304v3","paper_title":"Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models","paper_date":"2023-08-01","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112069,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-Llama3-70B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"56.1","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112070,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-7B (w/ code, SC, k=50)","metrics":{"Accuracy":"55.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112071,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MMOS-DeepSeekMath-7B(0-shot)","metrics":{"Accuracy":"55.0","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112072,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-Llama3-70B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"54.9","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112073,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PHP (GPT-4 model)","metrics":{"Accuracy":"53.9"},"paper_url":"https://arxiv.org/abs/2304.09797v6","paper_title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","paper_date":"2023-04-19","code_links":[{"title":"chuanyang-Zheng/Progressive-Hint","url":"https://github.com/chuanyang-Zheng/Progressive-Hint"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112074,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-DSMath-7B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"53.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112075,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Gemini Ultra (4-shot)","metrics":{"Accuracy":"53.2"},"paper_url":"https://arxiv.org/abs/2312.11805v5","paper_title":"Gemini: A Family of Highly Capable Multimodal Models","paper_date":"2023-12-19","code_links":[{"title":"valdecy/pybibx","url":"https://github.com/valdecy/pybibx"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112076,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-DSMath-7B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"52.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112077,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4 model (w/ code, PAL)","metrics":{"Accuracy":"51.8"},"paper_url":"https://arxiv.org/abs/2211.10435v2","paper_title":"PAL: Program-aided Language Models","paper_date":"2022-11-18","code_links":[{"title":"srush/minichain","url":"https://github.com/srush/minichain"},{"title":"RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox"},{"title":"allanj/dynamic-pal","url":"https://github.com/allanj/dynamic-pal"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112078,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DeepSeekMATH-RL-7B (greedy decoding)","metrics":{"Accuracy":"51.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.03300v3","paper_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","paper_date":"2024-02-05","code_links":[{"title":"shibing624/medicalgpt","url":"https://github.com/shibing624/medicalgpt"},{"title":"deepseek-ai/deepseek-math","url":"https://github.com/deepseek-ai/deepseek-math"},{"title":"openpsi-project/realhf","url":"https://github.com/openpsi-project/realhf"},{"title":"synthlabsai/big-math","url":"https://github.com/synthlabsai/big-math"},{"title":"yynil/rwkvinside","url":"https://github.com/yynil/rwkvinside"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112079,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"AlphaLLM (with MCTS)","metrics":{"Accuracy":"51"},"paper_url":"https://arxiv.org/abs/2404.12253v2","paper_title":"Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing","paper_date":"2024-04-18","code_links":[{"title":"yetianjhu/alphallm","url":"https://github.com/yetianjhu/alphallm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112080,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA-Code 34B (w/ code)","metrics":{"Accuracy":"50.8","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112081,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Accuracy":"50.7","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112082,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 540B (maj1@k, k=64)","metrics":{"Accuracy":"50.3"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112083,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA 70B (w/ code)","metrics":{"Accuracy":"49.7","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112084,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MMOS-CODE-34B(0-shot)","metrics":{"Accuracy":"49.5","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112085,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DeepSeekMath-7B-KPMath-Plus","metrics":{"Accuracy":"48.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112086,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 2 (few-shot, k=4, SC)","metrics":{"Accuracy":"48.8"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112087,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Llemma-34B-KPMath-Plus","metrics":{"Accuracy":"48.6","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112088,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-34B (w/ code)","metrics":{"Accuracy":"48.3","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112089,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Shepherd + DeepSeek-67B (SFT on MetaMATH + PRM rerank, k=256)","metrics":{"Accuracy":"48.1","Parameters (Billions)":"67"},"paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","paper_date":"2023-12-14","code_links":[{"title":"hkust-nlp/b-star","url":"https://github.com/hkust-nlp/b-star"},{"title":"chang-github-00/llm-predictive-decoding","url":"https://github.com/chang-github-00/llm-predictive-decoding"},{"title":"peiyi9979/Math-Shepherd","url":"https://huggingface.co/datasets/peiyi9979/Math-Shepherd"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112090,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA-Code 13B (w/ code)","metrics":{"Accuracy":"48.1","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112091,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 8B (maj5@256)","metrics":{"Accuracy":"47.6","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112092,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Mistral-7B-KPMath-Plus","metrics":{"Accuracy":"46.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112093,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-Llama3-8B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"46.6","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112094,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-Llama2-70B (w/ code)","metrics":{"Accuracy":"46.3","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112095,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-13B (w/ code)","metrics":{"Accuracy":"45.5","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112096,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-Mistral-7B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"45.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112097,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-Llama3-8B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"45.3","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112098,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MathCoder-CL-34B","metrics":{"Accuracy":"45.2","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112099,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MathCoder-L-34B","metrics":{"Accuracy":"45.1","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112100,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MMIQC-72B","metrics":{"Accuracy":"45.0","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2401.09003v5","paper_title":"Augmenting Math Word Problems via Iterative Question Composing","paper_date":"2024-01-17","code_links":[{"title":"iiis-ai/iterativequestioncomposing","url":"https://github.com/iiis-ai/iterativequestioncomposing"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112101,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA-Code 7B (w/ code)","metrics":{"Accuracy":"44.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112102,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-Mistral-7B (w/ code)","metrics":{"Accuracy":"44.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112103,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MMOS-CODE-7B(0-shot)","metrics":{"Accuracy":"44.3","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112104,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenMath-CodeLlama-7B (w/ code)","metrics":{"Accuracy":"43.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112105,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Shepherd+Mistral-7B (SFT on MetaMATH + PRM RL+ PRM rerank, k=256)","metrics":{"Accuracy":"43.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","paper_date":"2023-12-14","code_links":[{"title":"hkust-nlp/b-star","url":"https://github.com/hkust-nlp/b-star"},{"title":"chang-github-00/llm-predictive-decoding","url":"https://github.com/chang-github-00/llm-predictive-decoding"},{"title":"peiyi9979/Math-Shepherd","url":"https://huggingface.co/datasets/peiyi9979/Math-Shepherd"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112106,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"DART-Math-Mistral-7B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"43.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112107,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 62B (maj1@k, k=64)","metrics":{"Accuracy":"43.4","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112108,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA 13B (w/ code)","metrics":{"Accuracy":"43.0","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112109,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-4","metrics":{"Accuracy":"42.5"},"paper_url":"https://arxiv.org/abs/2303.12712v5","paper_title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","paper_date":"2023-03-22","code_links":[{"title":"microsoft/guidance","url":"https://github.com/microsoft/guidance"},{"title":"gammatauai/leetcode-hard-gym","url":"https://github.com/gammatauai/leetcode-hard-gym"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112110,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"SFT-Mistral-7B","metrics":{"Accuracy":"41.8","Parameters (Billions)":"7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112111,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Llama2-13B-KPMath-Plus","metrics":{"Accuracy":"41","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112112,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"ToRA 7B (w/ code)","metrics":{"Accuracy":"40.1","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112113,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MathCoder-CL-13B","metrics":{"Accuracy":"35.9","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112114,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MuggleMATH-70B","metrics":{"Accuracy":"35.6","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","paper_date":"2023-10-09","code_links":[{"title":"ofa-sys/gsm8k-screl","url":"https://github.com/ofa-sys/gsm8k-screl"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112115,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 2 (few-shot, k=4, CoT)","metrics":{"Accuracy":"34.3"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112116,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 540B","metrics":{"Accuracy":"33.6","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112117,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 540B (5-shot) mCoT","metrics":{"Accuracy":"33.6","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112118,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Shepherd + Mistral-7B (SFT on MetaMATH + PRM RL)","metrics":{"Accuracy":"33.0","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","paper_date":"2023-12-14","code_links":[{"title":"hkust-nlp/b-star","url":"https://github.com/hkust-nlp/b-star"},{"title":"chang-github-00/llm-predictive-decoding","url":"https://github.com/chang-github-00/llm-predictive-decoding"},{"title":"peiyi9979/Math-Shepherd","url":"https://huggingface.co/datasets/peiyi9979/Math-Shepherd"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112119,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"WizardMath-7B-V1.1","metrics":{"Accuracy":"33.0","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112120,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Gemini Pro (4-shot)","metrics":{"Accuracy":"32.6"},"paper_url":"https://arxiv.org/abs/2312.11805v5","paper_title":"Gemini: A Family of Highly Capable Multimodal Models","paper_date":"2023-12-19","code_links":[{"title":"valdecy/pybibx","url":"https://github.com/valdecy/pybibx"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112121,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MuggleMATH-13B","metrics":{"Accuracy":"30.7","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","paper_date":"2023-10-09","code_links":[{"title":"ofa-sys/gsm8k-screl","url":"https://github.com/ofa-sys/gsm8k-screl"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112122,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MathCoder-CL-7B","metrics":{"Accuracy":"30.2","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112123,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MathCoder-L-13B","metrics":{"Accuracy":"29.9","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112124,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Qwen2idae-16x14B (4-shot)","metrics":{"Accuracy":"29.9"},"paper_url":"https://arxiv.org/abs/2401.02731v4","paper_title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","paper_date":"2024-01-05","code_links":[{"title":"wuhy68/parameter-efficient-moe","url":"https://github.com/wuhy68/parameter-efficient-moe"},{"title":"ShayekhBinIslam/openrag","url":"https://github.com/ShayekhBinIslam/openrag"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112125,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenChat-3.5-1210 7B","metrics":{"Accuracy":"28.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.11235v2","paper_title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","paper_date":"2023-09-20","code_links":[{"title":"imoneoi/openchat","url":"https://github.com/imoneoi/openchat"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112126,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"OpenChat-3.5 7B","metrics":{"Accuracy":"28.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.11235v2","paper_title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","paper_date":"2023-09-20","code_links":[{"title":"imoneoi/openchat","url":"https://github.com/imoneoi/openchat"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112127,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Mixtral 8x7B (maj@4)","metrics":{"Accuracy":"28.4"},"paper_url":"https://arxiv.org/abs/2401.04088v1","paper_title":"Mixtral of Experts","paper_date":"2024-01-08","code_links":[{"title":"jingyaogong/minimind","url":"https://github.com/jingyaogong/minimind"},{"title":"hit-scir/chinese-mixtral-8x7b","url":"https://github.com/hit-scir/chinese-mixtral-8x7b"},{"title":"ymcui/chinese-mixtral","url":"https://github.com/ymcui/chinese-mixtral"},{"title":"consequentai/fneval","url":"https://github.com/consequentai/fneval"},{"title":"kamanphoebe/look-into-moes","url":"https://github.com/kamanphoebe/look-into-moes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mixtral"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112128,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 62B (4-shot)","metrics":{"Accuracy":"27.6","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112129,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MetaMath 70B","metrics":{"Accuracy":"26.0","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","paper_date":"2023-09-21","code_links":[{"title":"meta-math/MetaMath","url":"https://github.com/meta-math/MetaMath"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112130,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MuggleMATH 7B","metrics":{"Accuracy":"25.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","paper_date":"2023-10-09","code_links":[{"title":"ofa-sys/gsm8k-screl","url":"https://github.com/ofa-sys/gsm8k-screl"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112131,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 8B (maj1@k, k=64)","metrics":{"Accuracy":"25.4","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112132,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MathCoder-L-7B","metrics":{"Accuracy":"23.3","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112133,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"WizardMath-70B-V1.0","metrics":{"Accuracy":"22.7","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112134,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Camelidae-8×34B (4-shot)","metrics":{"Accuracy":"22.6"},"paper_url":"https://arxiv.org/abs/2401.02731v4","paper_title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","paper_date":"2024-01-05","code_links":[{"title":"wuhy68/parameter-efficient-moe","url":"https://github.com/wuhy68/parameter-efficient-moe"},{"title":"ShayekhBinIslam/openrag","url":"https://github.com/ShayekhBinIslam/openrag"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112135,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MetaMath 13B","metrics":{"Accuracy":"22.5","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","paper_date":"2023-09-21","code_links":[{"title":"meta-math/MetaMath","url":"https://github.com/meta-math/MetaMath"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112136,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 65B (maj1@k)","metrics":{"Accuracy":"20.5","Parameters (Billions)":"65"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112137,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GAL 120B (5-shot) mCoT","metrics":{"Accuracy":"20.4","Parameters (Billions)":"120"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112138,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"MetaMath 7B","metrics":{"Accuracy":"19.4","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","paper_date":"2023-09-21","code_links":[{"title":"meta-math/MetaMath","url":"https://github.com/meta-math/MetaMath"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112139,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"davinci-002 175B","metrics":{"Accuracy":"19.1","Parameters (Billions)":"175"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112140,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Branch-Train-MiX 4x7B (sampling top-2 experts)","metrics":{"Accuracy":"17.8"},"paper_url":"https://arxiv.org/abs/2403.07816v1","paper_title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","paper_date":"2024-03-12","code_links":[{"title":"Leeroo-AI/mergoo","url":"https://github.com/Leeroo-AI/mergoo"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112141,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GAL 120B <work>","metrics":{"Accuracy":"16.6","Parameters (Billions)":"120"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112142,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 33B-maj1@k","metrics":{"Accuracy":"15.2","Parameters (Billions)":"33"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112143,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Minerva 8B","metrics":{"Accuracy":"14.1","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112144,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"WizardMath-13B-V1.0","metrics":{"Accuracy":"14.0","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112145,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Mistral 7B (maj@4)","metrics":{"Accuracy":"13.1","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.06825v1","paper_title":"Mistral 7B","paper_date":"2023-10-10","code_links":[{"title":"mistralai/mistral-src","url":"https://github.com/mistralai/mistral-src"},{"title":"facebookresearch/fairseq2","url":"https://github.com/facebookresearch/fairseq2"},{"title":"mgmalek/efficient_cross_entropy","url":"https://github.com/mgmalek/efficient_cross_entropy"},{"title":"ninglab/ecellm","url":"https://github.com/ninglab/ecellm"},{"title":"knowlab/bi-weekly-paper-presentation","url":"https://github.com/knowlab/bi-weekly-paper-presentation"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mistral"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112146,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GAL 30B (5-shot) mCoT","metrics":{"Accuracy":"12.7","Parameters (Billions)":"30"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112147,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"Mistral 7B (maj@4)","metrics":{"Accuracy":"12.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2401.04088v1","paper_title":"Mixtral of Experts","paper_date":"2024-01-08","code_links":[{"title":"jingyaogong/minimind","url":"https://github.com/jingyaogong/minimind"},{"title":"hit-scir/chinese-mixtral-8x7b","url":"https://github.com/hit-scir/chinese-mixtral-8x7b"},{"title":"ymcui/chinese-mixtral","url":"https://github.com/ymcui/chinese-mixtral"},{"title":"consequentai/fneval","url":"https://github.com/consequentai/fneval"},{"title":"kamanphoebe/look-into-moes","url":"https://github.com/kamanphoebe/look-into-moes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mixtral"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112148,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GAL 30B <work>","metrics":{"Accuracy":"11.4","Parameters (Billions)":"30"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112149,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"WizardMath-7B-V1.0","metrics":{"Accuracy":"10.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112150,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 65B","metrics":{"Accuracy":"10.6","Parameters (Billions)":"65"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112151,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 540B","metrics":{"Accuracy":"8.8","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112152,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 540B (5-shot) mCoT","metrics":{"Accuracy":"8.8","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112153,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 13B-maj1@k","metrics":{"Accuracy":"8.8","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112154,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 33B","metrics":{"Accuracy":"7.1","Parameters (Billions)":"33"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112155,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 7B-maj1@k","metrics":{"Accuracy":"6.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112156,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-2 (1.5B)","metrics":{"Accuracy":"6.9","Parameters (Billions)":"1.5"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112157,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-2 (0.7B)","metrics":{"Accuracy":"6.4","Parameters (Billions)":"0.7"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112158,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-2 (0.3B)","metrics":{"Accuracy":"6.2","Parameters (Billions)":"0.3"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112159,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-3 13B","metrics":{"Accuracy":"5.6","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112160,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 8B (fine-tuned)","metrics":{"Accuracy":"5.6","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112161,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-2 (0.1B)","metrics":{"Accuracy":"5.4","Parameters (Billions)":"0.1"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112162,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-3-175B (few-shot)","metrics":{"Accuracy":"5.2","Parameters (Billions)":"175"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112163,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-3 175B (8-shot)","metrics":{"Accuracy":"5.2","Parameters (Billions)":"175"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112164,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 62B","metrics":{"Accuracy":"4.4","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112165,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 13B","metrics":{"Accuracy":"3.9","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112166,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-3-13B (few-shot)","metrics":{"Accuracy":"3.0","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112167,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"LLaMA 7B","metrics":{"Accuracy":"2.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112168,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"GPT-3 2.7B","metrics":{"Accuracy":"2.9","Parameters (Billions)":"2.7"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112169,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MATH","model_name":"PaLM 8B","metrics":{"Accuracy":"1.5","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120384,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Gemini 2.0 Flash Experimental","metrics":{"Accuracy":"89.7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120385,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Qwen2.5-Math-72B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"88.1","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120386,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-4 Turbo (MACM, w/code, voting)","metrics":{"Accuracy":"87.920"},"paper_url":"https://arxiv.org/abs/2404.04735v2","paper_title":"MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems","paper_date":"2024-04-06","code_links":[{"title":"bin123apple/macm","url":"https://github.com/bin123apple/macm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120387,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Qwen2.5-Math-72B-Instruct(COT,Greedy)","metrics":{"Accuracy":"85.9","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120388,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Qwen2.5-Math-7B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"85.2","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120389,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-4-code model (CSV, w/ code, SC, k=16)","metrics":{"Accuracy":"84.3"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120390,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Qwen2-Math-72B-Instruct(greedy)","metrics":{"Accuracy":"84.0","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2407.10671v4","paper_title":"Qwen2 Technical Report","paper_date":"2024-07-15","code_links":[{"title":"qwenlm/qwen1.5","url":"https://github.com/qwenlm/qwen1.5"},{"title":"qwenlm/qwen2","url":"https://github.com/qwenlm/qwen2"},{"title":"vicentvankor/sun-shine","url":"https://github.com/vicentvankor/sun-shine"},{"title":"ziye2chen/LLMs-for-Mathematical-Analysis","url":"https://github.com/ziye2chen/LLMs-for-Mathematical-Analysis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/qwen2_moe"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/qwen2"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120391,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Qwen2.5-Math-7B-Instruct(COT,Greedy)","metrics":{"Accuracy":"83.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120392,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Qwen2.5-Math-1.5B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"79.9","Parameters (Billions)":"1.5"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120393,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath2-Llama3.1-70B (majority@256)","metrics":{"Accuracy":"79.6"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120394,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath2-Llama3.1-8B (majority@256)","metrics":{"Accuracy":"76.1"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120395,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Qwen2.5-Math-1.5B-Instruct(COT,Greedy)","metrics":{"Accuracy":"75.8","Parameters (Billions)":"1.5"},"paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120396,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-4-code model (CSV, w/ code)","metrics":{"Accuracy":"73.5"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120397,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"CR (GPT-4-turbo model, w/ code)","metrics":{"Accuracy":"72.2"},"paper_url":"https://arxiv.org/abs/2308.04371v6","paper_title":"Cumulative Reasoning with Large Language Models","paper_date":"2023-08-08","code_links":[{"title":"iiis-ai/cumulative-reasoning","url":"https://github.com/iiis-ai/cumulative-reasoning"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120398,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath2-Llama3.1-70B","metrics":{"Accuracy":"71.9"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120399,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"LogicNet (with code interpreter)","metrics":{"Accuracy":"71.2"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120400,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Qwen2-72B-Instruct-Step-DPO (0-shot CoT, w/o code)","metrics":{"Accuracy":"70.8"},"paper_url":"https://arxiv.org/abs/2406.18629v1","paper_title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","paper_date":"2024-06-26","code_links":[{"title":"dvlab-research/step-dpo","url":"https://github.com/dvlab-research/step-dpo"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120401,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-4-code model (w/ code)","metrics":{"Accuracy":"69.7"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120402,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath2-Llama3.1-8B","metrics":{"Accuracy":"67.8"},"paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","paper_date":"2024-10-02","code_links":[{"title":"NVIDIA/NeMo-Skills","url":"https://github.com/NVIDIA/NeMo-Skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120403,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"AlphaMath-7B-SBS@3","metrics":{"Accuracy":"66.3"},"paper_url":"https://arxiv.org/abs/2405.03553v3","paper_title":"AlphaMath Almost Zero: Process Supervision without Process","paper_date":"2024-05-06","code_links":[{"title":"MARIO-Math-Reasoning/Super_MARIO","url":"https://github.com/MARIO-Math-Reasoning/Super_MARIO"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120404,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Minerva 62B (maj5@256)","metrics":{"Accuracy":"64.9","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120405,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"DAMOMath-7B","metrics":{"Accuracy":"64.5","Parameters (Billions)":"7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120406,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MMOS-DeepSeekMath-7B(0-shot,k=50)","metrics":{"Accuracy":"63.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120407,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-4-code model (w/o code)","metrics":{"Accuracy":"60.8"},"paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","paper_date":"2023-08-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120408,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath-CodeLlama-70B (w/ code, SC, k=50)","metrics":{"Accuracy":"60.4","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120409,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath-CodeLlama-34B (w/ code, SC, k=50)","metrics":{"Accuracy":"60.2","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120410,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"ToRA-Code 34B model (w/ code, SC, k=50)","metrics":{"Accuracy":"60.0","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120411,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"DeepSeekMATH-RL-7B (w/ code, greedy decoding)","metrics":{"Accuracy":"58.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.03300v3","paper_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","paper_date":"2024-02-05","code_links":[{"title":"shibing624/medicalgpt","url":"https://github.com/shibing624/medicalgpt"},{"title":"deepseek-ai/deepseek-math","url":"https://github.com/deepseek-ai/deepseek-math"},{"title":"openpsi-project/realhf","url":"https://github.com/openpsi-project/realhf"},{"title":"synthlabsai/big-math","url":"https://github.com/synthlabsai/big-math"},{"title":"yynil/rwkvinside","url":"https://github.com/yynil/rwkvinside"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120412,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath-Llama2-70B (w/ code, SC, k=50)","metrics":{"Accuracy":"58.3","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120413,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"CR (GPT-4 model, w/o code)","metrics":{"Accuracy":"58.0"},"paper_url":"https://arxiv.org/abs/2308.04371v6","paper_title":"Cumulative Reasoning with Large Language Models","paper_date":"2023-08-08","code_links":[{"title":"iiis-ai/cumulative-reasoning","url":"https://github.com/iiis-ai/cumulative-reasoning"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120414,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath-CodeLlama-13B (w/ code, SC, k=50)","metrics":{"Accuracy":"57.6","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120415,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath-Mistral-7B (w/ code, SC, k=50)","metrics":{"Accuracy":"57.2","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120416,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"ToRA 70B (w/ code, SC, k=50)","metrics":{"Accuracy":"56.9","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120417,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"SKiC (GPT-4 model)","metrics":{"Accuracy":"56.4"},"paper_url":"https://arxiv.org/abs/2308.00304v3","paper_title":"Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models","paper_date":"2023-08-01","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120418,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"DART-Math-Llama3-70B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"56.1","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120419,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath-CodeLlama-7B (w/ code, SC, k=50)","metrics":{"Accuracy":"55.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120420,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MMOS-DeepSeekMath-7B(0-shot)","metrics":{"Accuracy":"55.0","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120421,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"DART-Math-Llama3-70B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"54.9","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120422,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"PHP (GPT-4 model)","metrics":{"Accuracy":"53.9"},"paper_url":"https://arxiv.org/abs/2304.09797v6","paper_title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","paper_date":"2023-04-19","code_links":[{"title":"chuanyang-Zheng/Progressive-Hint","url":"https://github.com/chuanyang-Zheng/Progressive-Hint"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120423,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"DART-Math-DSMath-7B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"53.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120424,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Gemini Ultra (4-shot)","metrics":{"Accuracy":"53.2"},"paper_url":"https://arxiv.org/abs/2312.11805v5","paper_title":"Gemini: A Family of Highly Capable Multimodal Models","paper_date":"2023-12-19","code_links":[{"title":"valdecy/pybibx","url":"https://github.com/valdecy/pybibx"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120425,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"DART-Math-DSMath-7B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"52.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120426,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-4 model (w/ code, PAL)","metrics":{"Accuracy":"51.8"},"paper_url":"https://arxiv.org/abs/2211.10435v2","paper_title":"PAL: Program-aided Language Models","paper_date":"2022-11-18","code_links":[{"title":"srush/minichain","url":"https://github.com/srush/minichain"},{"title":"RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox"},{"title":"allanj/dynamic-pal","url":"https://github.com/allanj/dynamic-pal"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120427,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"DeepSeekMATH-RL-7B (greedy decoding)","metrics":{"Accuracy":"51.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.03300v3","paper_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","paper_date":"2024-02-05","code_links":[{"title":"shibing624/medicalgpt","url":"https://github.com/shibing624/medicalgpt"},{"title":"deepseek-ai/deepseek-math","url":"https://github.com/deepseek-ai/deepseek-math"},{"title":"openpsi-project/realhf","url":"https://github.com/openpsi-project/realhf"},{"title":"synthlabsai/big-math","url":"https://github.com/synthlabsai/big-math"},{"title":"yynil/rwkvinside","url":"https://github.com/yynil/rwkvinside"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120428,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"AlphaLLM (with MCTS)","metrics":{"Accuracy":"51"},"paper_url":"https://arxiv.org/abs/2404.12253v2","paper_title":"Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing","paper_date":"2024-04-18","code_links":[{"title":"yetianjhu/alphallm","url":"https://github.com/yetianjhu/alphallm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120429,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"ToRA-Code 34B (w/ code)","metrics":{"Accuracy":"50.8","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120430,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Accuracy":"50.7","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120431,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Minerva 540B (maj1@k, k=64)","metrics":{"Accuracy":"50.3"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120432,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"ToRA 70B (w/ code)","metrics":{"Accuracy":"49.7","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120433,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MMOS-CODE-34B(0-shot)","metrics":{"Accuracy":"49.5","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120434,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"DeepSeekMath-7B-KPMath-Plus","metrics":{"Accuracy":"48.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120435,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"PaLM 2 (few-shot, k=4, SC)","metrics":{"Accuracy":"48.8"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120436,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Llemma-34B-KPMath-Plus","metrics":{"Accuracy":"48.6","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120437,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath-CodeLlama-34B (w/ code)","metrics":{"Accuracy":"48.3","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120438,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Shepherd + DeepSeek-67B (SFT on MetaMATH + PRM rerank, k=256)","metrics":{"Accuracy":"48.1","Parameters (Billions)":"67"},"paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","paper_date":"2023-12-14","code_links":[{"title":"hkust-nlp/b-star","url":"https://github.com/hkust-nlp/b-star"},{"title":"chang-github-00/llm-predictive-decoding","url":"https://github.com/chang-github-00/llm-predictive-decoding"},{"title":"peiyi9979/Math-Shepherd","url":"https://huggingface.co/datasets/peiyi9979/Math-Shepherd"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120439,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"ToRA-Code 13B (w/ code)","metrics":{"Accuracy":"48.1","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120440,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Minerva 8B (maj5@256)","metrics":{"Accuracy":"47.6","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120441,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Mistral-7B-KPMath-Plus","metrics":{"Accuracy":"46.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120442,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"DART-Math-Llama3-8B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"46.6","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120443,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath-Llama2-70B (w/ code)","metrics":{"Accuracy":"46.3","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120444,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath-CodeLlama-13B (w/ code)","metrics":{"Accuracy":"45.5","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120445,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"DART-Math-Mistral-7B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"45.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120446,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"DART-Math-Llama3-8B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"45.3","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120447,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MathCoder-CL-34B","metrics":{"Accuracy":"45.2","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120448,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MathCoder-L-34B","metrics":{"Accuracy":"45.1","Parameters (Billions)":"34"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120449,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MMIQC-72B","metrics":{"Accuracy":"45.0","Parameters (Billions)":"72"},"paper_url":"https://arxiv.org/abs/2401.09003v5","paper_title":"Augmenting Math Word Problems via Iterative Question Composing","paper_date":"2024-01-17","code_links":[{"title":"iiis-ai/iterativequestioncomposing","url":"https://github.com/iiis-ai/iterativequestioncomposing"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120450,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"ToRA-Code 7B (w/ code)","metrics":{"Accuracy":"44.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120451,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath-Mistral-7B (w/ code)","metrics":{"Accuracy":"44.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120452,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MMOS-CODE-7B(0-shot)","metrics":{"Accuracy":"44.3","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120453,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenMath-CodeLlama-7B (w/ code)","metrics":{"Accuracy":"43.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120454,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Shepherd+Mistral-7B (SFT on MetaMATH + PRM RL+ PRM rerank, k=256)","metrics":{"Accuracy":"43.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","paper_date":"2023-12-14","code_links":[{"title":"hkust-nlp/b-star","url":"https://github.com/hkust-nlp/b-star"},{"title":"chang-github-00/llm-predictive-decoding","url":"https://github.com/chang-github-00/llm-predictive-decoding"},{"title":"peiyi9979/Math-Shepherd","url":"https://huggingface.co/datasets/peiyi9979/Math-Shepherd"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120455,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"DART-Math-Mistral-7B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"43.5","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","paper_date":"2024-06-18","code_links":[{"title":"hkust-nlp/dart-math","url":"https://github.com/hkust-nlp/dart-math"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120456,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Minerva 62B (maj1@k, k=64)","metrics":{"Accuracy":"43.4","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120457,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"ToRA 13B (w/ code)","metrics":{"Accuracy":"43.0","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120458,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-4","metrics":{"Accuracy":"42.5"},"paper_url":"https://arxiv.org/abs/2303.12712v5","paper_title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","paper_date":"2023-03-22","code_links":[{"title":"microsoft/guidance","url":"https://github.com/microsoft/guidance"},{"title":"gammatauai/leetcode-hard-gym","url":"https://github.com/gammatauai/leetcode-hard-gym"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120459,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"SFT-Mistral-7B","metrics":{"Accuracy":"41.8","Parameters (Billions)":"7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120460,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Llama2-13B-KPMath-Plus","metrics":{"Accuracy":"41","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","paper_date":"2024-03-04","code_links":[],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120461,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"ToRA 7B (w/ code)","metrics":{"Accuracy":"40.1","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","paper_date":"2023-09-29","code_links":[{"title":"microsoft/tora","url":"https://github.com/microsoft/tora"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120462,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MathCoder-CL-13B","metrics":{"Accuracy":"35.9","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120463,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MuggleMATH-70B","metrics":{"Accuracy":"35.6","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","paper_date":"2023-10-09","code_links":[{"title":"ofa-sys/gsm8k-screl","url":"https://github.com/ofa-sys/gsm8k-screl"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120464,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"PaLM 2 (few-shot, k=4, CoT)","metrics":{"Accuracy":"34.3"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120465,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Minerva 540B","metrics":{"Accuracy":"33.6","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120466,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Minerva 540B (5-shot) mCoT","metrics":{"Accuracy":"33.6","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120467,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Shepherd + Mistral-7B (SFT on MetaMATH + PRM RL)","metrics":{"Accuracy":"33.0","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","paper_date":"2023-12-14","code_links":[{"title":"hkust-nlp/b-star","url":"https://github.com/hkust-nlp/b-star"},{"title":"chang-github-00/llm-predictive-decoding","url":"https://github.com/chang-github-00/llm-predictive-decoding"},{"title":"peiyi9979/Math-Shepherd","url":"https://huggingface.co/datasets/peiyi9979/Math-Shepherd"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120468,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"WizardMath-7B-V1.1","metrics":{"Accuracy":"33.0","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120469,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Gemini Pro (4-shot)","metrics":{"Accuracy":"32.6"},"paper_url":"https://arxiv.org/abs/2312.11805v5","paper_title":"Gemini: A Family of Highly Capable Multimodal Models","paper_date":"2023-12-19","code_links":[{"title":"valdecy/pybibx","url":"https://github.com/valdecy/pybibx"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120470,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MuggleMATH-13B","metrics":{"Accuracy":"30.7","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","paper_date":"2023-10-09","code_links":[{"title":"ofa-sys/gsm8k-screl","url":"https://github.com/ofa-sys/gsm8k-screl"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120471,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MathCoder-CL-7B","metrics":{"Accuracy":"30.2","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120472,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MathCoder-L-13B","metrics":{"Accuracy":"29.9","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120473,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Qwen2idae-16x14B (4-shot)","metrics":{"Accuracy":"29.9"},"paper_url":"https://arxiv.org/abs/2401.02731v4","paper_title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","paper_date":"2024-01-05","code_links":[{"title":"wuhy68/parameter-efficient-moe","url":"https://github.com/wuhy68/parameter-efficient-moe"},{"title":"ShayekhBinIslam/openrag","url":"https://github.com/ShayekhBinIslam/openrag"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120474,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenChat-3.5-1210 7B","metrics":{"Accuracy":"28.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.11235v2","paper_title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","paper_date":"2023-09-20","code_links":[{"title":"imoneoi/openchat","url":"https://github.com/imoneoi/openchat"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120475,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"OpenChat-3.5 7B","metrics":{"Accuracy":"28.6","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.11235v2","paper_title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","paper_date":"2023-09-20","code_links":[{"title":"imoneoi/openchat","url":"https://github.com/imoneoi/openchat"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120476,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Mixtral 8x7B (maj@4)","metrics":{"Accuracy":"28.4"},"paper_url":"https://arxiv.org/abs/2401.04088v1","paper_title":"Mixtral of Experts","paper_date":"2024-01-08","code_links":[{"title":"jingyaogong/minimind","url":"https://github.com/jingyaogong/minimind"},{"title":"hit-scir/chinese-mixtral-8x7b","url":"https://github.com/hit-scir/chinese-mixtral-8x7b"},{"title":"ymcui/chinese-mixtral","url":"https://github.com/ymcui/chinese-mixtral"},{"title":"consequentai/fneval","url":"https://github.com/consequentai/fneval"},{"title":"kamanphoebe/look-into-moes","url":"https://github.com/kamanphoebe/look-into-moes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mixtral"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120477,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Minerva 62B (4-shot)","metrics":{"Accuracy":"27.6","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120478,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MetaMath 70B","metrics":{"Accuracy":"26.0","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","paper_date":"2023-09-21","code_links":[{"title":"meta-math/MetaMath","url":"https://github.com/meta-math/MetaMath"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120479,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MuggleMATH 7B","metrics":{"Accuracy":"25.8","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","paper_date":"2023-10-09","code_links":[{"title":"ofa-sys/gsm8k-screl","url":"https://github.com/ofa-sys/gsm8k-screl"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120480,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Minerva 8B (maj1@k, k=64)","metrics":{"Accuracy":"25.4","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120481,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MathCoder-L-7B","metrics":{"Accuracy":"23.3","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","paper_date":"2023-10-05","code_links":[{"title":"mathllm/mathcoder","url":"https://github.com/mathllm/mathcoder"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120482,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"WizardMath-70B-V1.0","metrics":{"Accuracy":"22.7","Parameters (Billions)":"70"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120483,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Camelidae-8×34B (4-shot)","metrics":{"Accuracy":"22.6"},"paper_url":"https://arxiv.org/abs/2401.02731v4","paper_title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","paper_date":"2024-01-05","code_links":[{"title":"wuhy68/parameter-efficient-moe","url":"https://github.com/wuhy68/parameter-efficient-moe"},{"title":"ShayekhBinIslam/openrag","url":"https://github.com/ShayekhBinIslam/openrag"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120484,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MetaMath 13B","metrics":{"Accuracy":"22.5","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","paper_date":"2023-09-21","code_links":[{"title":"meta-math/MetaMath","url":"https://github.com/meta-math/MetaMath"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120485,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"LLaMA 65B (maj1@k)","metrics":{"Accuracy":"20.5","Parameters (Billions)":"65"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120486,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GAL 120B (5-shot) mCoT","metrics":{"Accuracy":"20.4","Parameters (Billions)":"120"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120487,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"MetaMath 7B","metrics":{"Accuracy":"19.4","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","paper_date":"2023-09-21","code_links":[{"title":"meta-math/MetaMath","url":"https://github.com/meta-math/MetaMath"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120488,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"davinci-002 175B","metrics":{"Accuracy":"19.1","Parameters (Billions)":"175"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120489,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Branch-Train-MiX 4x7B (sampling top-2 experts)","metrics":{"Accuracy":"17.8"},"paper_url":"https://arxiv.org/abs/2403.07816v1","paper_title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","paper_date":"2024-03-12","code_links":[{"title":"Leeroo-AI/mergoo","url":"https://github.com/Leeroo-AI/mergoo"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120490,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GAL 120B <work>","metrics":{"Accuracy":"16.6","Parameters (Billions)":"120"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120491,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"LLaMA 33B-maj1@k","metrics":{"Accuracy":"15.2","Parameters (Billions)":"33"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120492,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Minerva 8B","metrics":{"Accuracy":"14.1","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120493,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"WizardMath-13B-V1.0","metrics":{"Accuracy":"14.0","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120494,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Mistral 7B (maj@4)","metrics":{"Accuracy":"13.1","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2310.06825v1","paper_title":"Mistral 7B","paper_date":"2023-10-10","code_links":[{"title":"mistralai/mistral-src","url":"https://github.com/mistralai/mistral-src"},{"title":"facebookresearch/fairseq2","url":"https://github.com/facebookresearch/fairseq2"},{"title":"mgmalek/efficient_cross_entropy","url":"https://github.com/mgmalek/efficient_cross_entropy"},{"title":"ninglab/ecellm","url":"https://github.com/ninglab/ecellm"},{"title":"knowlab/bi-weekly-paper-presentation","url":"https://github.com/knowlab/bi-weekly-paper-presentation"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mistral"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120495,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GAL 30B (5-shot) mCoT","metrics":{"Accuracy":"12.7","Parameters (Billions)":"30"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120496,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"Mistral 7B (maj@4)","metrics":{"Accuracy":"12.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2401.04088v1","paper_title":"Mixtral of Experts","paper_date":"2024-01-08","code_links":[{"title":"jingyaogong/minimind","url":"https://github.com/jingyaogong/minimind"},{"title":"hit-scir/chinese-mixtral-8x7b","url":"https://github.com/hit-scir/chinese-mixtral-8x7b"},{"title":"ymcui/chinese-mixtral","url":"https://github.com/ymcui/chinese-mixtral"},{"title":"consequentai/fneval","url":"https://github.com/consequentai/fneval"},{"title":"kamanphoebe/look-into-moes","url":"https://github.com/kamanphoebe/look-into-moes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mixtral"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120497,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GAL 30B <work>","metrics":{"Accuracy":"11.4","Parameters (Billions)":"30"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120498,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"WizardMath-7B-V1.0","metrics":{"Accuracy":"10.7","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","paper_date":"2023-08-18","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120499,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"LLaMA 65B","metrics":{"Accuracy":"10.6","Parameters (Billions)":"65"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120500,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"PaLM 540B","metrics":{"Accuracy":"8.8","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120501,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"PaLM 540B (5-shot) mCoT","metrics":{"Accuracy":"8.8","Parameters (Billions)":"540"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120502,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"LLaMA 13B-maj1@k","metrics":{"Accuracy":"8.8","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120503,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"LLaMA 33B","metrics":{"Accuracy":"7.1","Parameters (Billions)":"33"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120504,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"LLaMA 7B-maj1@k","metrics":{"Accuracy":"6.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120505,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-2 (1.5B)","metrics":{"Accuracy":"6.9","Parameters (Billions)":"1.5"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120506,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-2 (0.7B)","metrics":{"Accuracy":"6.4","Parameters (Billions)":"0.7"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120507,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-2 (0.3B)","metrics":{"Accuracy":"6.2","Parameters (Billions)":"0.3"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120508,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-3 13B","metrics":{"Accuracy":"5.6","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120509,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"PaLM 8B (fine-tuned)","metrics":{"Accuracy":"5.6","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120510,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-2 (0.1B)","metrics":{"Accuracy":"5.4","Parameters (Billions)":"0.1"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120511,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-3-175B (few-shot)","metrics":{"Accuracy":"5.2","Parameters (Billions)":"175"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120512,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-3 175B (8-shot)","metrics":{"Accuracy":"5.2","Parameters (Billions)":"175"},"paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","paper_date":"2022-11-16","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120513,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"PaLM 62B","metrics":{"Accuracy":"4.4","Parameters (Billions)":"62"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120514,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"LLaMA 13B","metrics":{"Accuracy":"3.9","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120515,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-3-13B (few-shot)","metrics":{"Accuracy":"3.0","Parameters (Billions)":"13"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120516,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"LLaMA 7B","metrics":{"Accuracy":"2.9","Parameters (Billions)":"7"},"paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","paper_date":"2023-02-27","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"meta-llama/llama","url":"https://github.com/meta-llama/llama"},{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"tatsu-lab/stanford_alpaca","url":"https://github.com/tatsu-lab/stanford_alpaca"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"nebuly-ai/nebullvm","url":"https://github.com/nebuly-ai/nebullvm/tree/main/apps/accelerate/chatllama"},{"title":"Lightning-AI/lit-llama","url":"https://github.com/Lightning-AI/lit-llama"},{"title":"facico/chinese-vicuna","url":"https://github.com/facico/chinese-vicuna"},{"title":"qwopqwop200/GPTQ-for-LLaMa","url":"https://github.com/qwopqwop200/GPTQ-for-LLaMa"},{"title":"phoebussi/alpaca-cot","url":"https://github.com/phoebussi/alpaca-cot"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"xusenlinzy/api-for-open-llm","url":"https://github.com/xusenlinzy/api-for-open-llm"},{"title":"guinmoon/llmfarm","url":"https://github.com/guinmoon/llmfarm"},{"title":"aethercortex/llama-x","url":"https://github.com/aethercortex/llama-x"},{"title":"beomi/koalpaca","url":"https://github.com/beomi/koalpaca"},{"title":"freedomintelligence/huatuogpt","url":"https://github.com/freedomintelligence/huatuogpt"},{"title":"icalk-nlp/educhat","url":"https://github.com/icalk-nlp/educhat"},{"title":"ecnu-icalk/educhat","url":"https://github.com/ecnu-icalk/educhat"},{"title":"ganjinzero/rrhf","url":"https://github.com/ganjinzero/rrhf"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"chaoyi-wu/pmc-llama","url":"https://github.com/chaoyi-wu/pmc-llama"},{"title":"kbressem/medalpaca","url":"https://github.com/kbressem/medalpaca"},{"title":"chaoyi-wu/finetune_llama","url":"https://github.com/chaoyi-wu/finetune_llama"},{"title":"ofa-sys/expertllama","url":"https://github.com/ofa-sys/expertllama"},{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"fsoft-ai4code/codecapybara","url":"https://github.com/fsoft-ai4code/codecapybara"},{"title":"kayvr/token-hawk","url":"https://github.com/kayvr/token-hawk"},{"title":"ntunlplab/traditional-chinese-alpaca","url":"https://github.com/ntunlplab/traditional-chinese-alpaca"},{"title":"teelinsan/camoscio","url":"https://github.com/teelinsan/camoscio"},{"title":"replicate/cog_stanford_alpaca","url":"https://github.com/replicate/cog_stanford_alpaca"},{"title":"greenbitai/low_bit_llama","url":"https://github.com/greenbitai/low_bit_llama"},{"title":"krafton-ai/korani","url":"https://github.com/krafton-ai/korani"},{"title":"yuanmu97/secure-transformer-inference","url":"https://github.com/yuanmu97/secure-transformer-inference"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"hamishivi/easylm","url":"https://github.com/hamishivi/easylm"},{"title":"xvyaward/owq","url":"https://github.com/xvyaward/owq"},{"title":"vcskaushik/LLMzip","url":"https://github.com/vcskaushik/LLMzip"},{"title":"batsresearch/alfred","url":"https://github.com/batsresearch/alfred"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"},{"title":"fajri91/indommlu","url":"https://github.com/fajri91/indommlu"},{"title":"akanyaani/miniLLAMA","url":"https://github.com/akanyaani/miniLLAMA"},{"title":"stanfordbdhg/llama.cpp","url":"https://github.com/stanfordbdhg/llama.cpp"},{"title":"facebookresearch/chai","url":"https://github.com/facebookresearch/chai"},{"title":"aozhongzhang/magr","url":"https://github.com/aozhongzhang/magr"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"ohadrubin/rpt","url":"https://github.com/ohadrubin/rpt"},{"title":"ecolab-postech/owq","url":"https://github.com/ecolab-postech/owq"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/llama2"},{"title":"Mind23-2/MindCode-140","url":"https://github.com/Mind23-2/MindCode-140"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/llama"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120517,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"GPT-3 2.7B","metrics":{"Accuracy":"2.9","Parameters (Billions)":"2.7"},"paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","paper_date":"2021-03-05","code_links":[{"title":"hendrycks/math","url":"https://github.com/hendrycks/math"},{"title":"openai/minif2f","url":"https://github.com/openai/minif2f"},{"title":"facebookresearch/minif2f","url":"https://github.com/facebookresearch/minif2f"},{"title":"rah4927/lean-dojo-mew","url":"https://github.com/rah4927/lean-dojo-mew"},{"title":"radzim/obfuscated","url":"https://github.com/radzim/obfuscated"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120518,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MATH","model_name":"PaLM 8B","metrics":{"Accuracy":"1.5","Parameters (Billions)":"8"},"paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","paper_date":"2022-06-29","code_links":[{"title":"gair-nlp/abel","url":"https://github.com/gair-nlp/abel"}],"metrics_order":"[\"Accuracy\", \"Parameters (Billions)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]}]}