{"task":"Math Word Problem Solving","dataset":"MAWPS","metric_names":["Accuracy (%)"],"rows":[{"id":25348,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Accuracy (%)":"95.7"},"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 (%)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25349,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"MsAT-DeductReasoner","metrics":{"Accuracy (%)":"94.3"},"paper_url":"https://arxiv.org/abs/2306.01707v3","paper_title":"Learning Multi-Step Reasoning by Solving Arithmetic Tasks","paper_date":"2023-06-02","code_links":[{"title":"TianduoWang/MsAT","url":"https://github.com/TianduoWang/MsAT"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25350,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"ATHENA (roberta-large)","metrics":{"Accuracy (%)":"93"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25351,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Multi-view","metrics":{"Accuracy (%)":"92.3"},"paper_url":"https://arxiv.org/abs/2210.11694v2","paper_title":"Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem","paper_date":"2022-10-21","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25352,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Exp-Tree","metrics":{"Accuracy (%)":"92.3"},"paper_url":"https://arxiv.org/abs/2310.09619v3","paper_title":"An Expression Tree Decoding Strategy for Mathematical Equation Generation","paper_date":"2023-10-14","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25353,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"ATHENA (roberta-base)","metrics":{"Accuracy (%)":"92.2"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25354,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Roberta-DeductReasoner","metrics":{"Accuracy (%)":"92"},"paper_url":"https://arxiv.org/abs/2203.10316v4","paper_title":"Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction","paper_date":"2022-03-19","code_links":[{"title":"allanj/deductive-mwp","url":"https://github.com/allanj/deductive-mwp"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25355,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"DeBERTa (PM + VM)","metrics":{"Accuracy (%)":"91.0"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25356,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"EPT","metrics":{"Accuracy (%)":"88.7"},"paper_url":"https://aclanthology.org/2022.acl-long.305","paper_title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","paper_date":null,"code_links":[{"title":"snucclab/ept-x","url":"https://github.com/snucclab/ept-x"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25357,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Graph2Tree with RoBERTa","metrics":{"Accuracy (%)":"88.7"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25358,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GTS with RoBERTa","metrics":{"Accuracy (%)":"88.5"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25359,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GEO","metrics":{"Accuracy (%)":"85.1"},"paper_url":"https://aclanthology.org/2020.coling-main.38","paper_title":"Generating Equation by Utilizing Operators : GEO model","paper_date":"2020-12-01","code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25360,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"EPT-X","metrics":{"Accuracy (%)":"84.57"},"paper_url":"https://aclanthology.org/2022.acl-long.305","paper_title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","paper_date":null,"code_links":[{"title":"snucclab/ept-x","url":"https://github.com/snucclab/ept-x"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25361,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"EPT","metrics":{"Accuracy (%)":"84.51"},"paper_url":"https://aclanthology.org/2020.emnlp-main.308","paper_title":"Point to the Expression: Solving Algebraic Word Problems using the Expression-Pointer Transformer Model","paper_date":null,"code_links":[{"title":"snucclab/EPT","url":"https://github.com/snucclab/EPT"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25362,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Graph2Tree","metrics":{"Accuracy (%)":"83.7"},"paper_url":"https://aclanthology.org/2020.acl-main.362","paper_title":"Graph-to-Tree Learning for Solving Math Word Problems","paper_date":"2020-07-01","code_links":[{"title":"2003pro/Graph2Tree","url":"https://github.com/2003pro/Graph2Tree"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25363,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"LLaMA 2-Chat","metrics":{"Accuracy (%)":"82.4"},"paper_url":"https://arxiv.org/abs/2307.09288v2","paper_title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","paper_date":"2023-07-18","code_links":[{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"Lightning-AI/lit-gpt","url":"https://github.com/Lightning-AI/lit-gpt"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"IBM/Dromedary","url":"https://github.com/IBM/Dromedary"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"xverse-ai/xverse-13b","url":"https://github.com/xverse-ai/xverse-13b"},{"title":"usyd-fsalab/fp6_llm","url":"https://github.com/usyd-fsalab/fp6_llm"},{"title":"rijgersberg/geitje","url":"https://github.com/rijgersberg/geitje"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"glb400/Toy-RecLM","url":"https://github.com/glb400/Toy-RecLM"},{"title":"ninglab/ecellm","url":"https://github.com/ninglab/ecellm"},{"title":"zurichnlp/contradecode","url":"https://github.com/zurichnlp/contradecode"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"idiap/abroad-re","url":"https://github.com/idiap/abroad-re"},{"title":"meetyou-ai-lab/can-mc-evaluate-llms","url":"https://github.com/meetyou-ai-lab/can-mc-evaluate-llms"},{"title":"xuetianci/pacit","url":"https://github.com/xuetianci/pacit"},{"title":"coastalcph/eu-politics-llms","url":"https://github.com/coastalcph/eu-politics-llms"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25364,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GPT-3.5 turbo (175B)","metrics":{"Accuracy (%)":"80.3"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25365,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Toolformer","metrics":{"Accuracy (%)":"44.0"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25366,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GPT-3 (175B)","metrics":{"Accuracy (%)":"19.8"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25367,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Toolformer (disabled)","metrics":{"Accuracy (%)":"15.0"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25368,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GPT-J","metrics":{"Accuracy (%)":"9.9"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25369,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GPT-J + CC","metrics":{"Accuracy (%)":"9.3"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25370,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"OPT (66B)","metrics":{"Accuracy (%)":"7.9"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25371,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GPT-3 text-curie-001 (13B)","metrics":{"Accuracy (%)":"4.09"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25372,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GPT-3 text-babbage-001 (6.7B)","metrics":{"Accuracy (%)":"2.76"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94926,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Accuracy (%)":"95.7"},"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 (%)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94927,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"MsAT-DeductReasoner","metrics":{"Accuracy (%)":"94.3"},"paper_url":"https://arxiv.org/abs/2306.01707v3","paper_title":"Learning Multi-Step Reasoning by Solving Arithmetic Tasks","paper_date":"2023-06-02","code_links":[{"title":"TianduoWang/MsAT","url":"https://github.com/TianduoWang/MsAT"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94928,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"ATHENA (roberta-large)","metrics":{"Accuracy (%)":"93"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94929,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"Multi-view","metrics":{"Accuracy (%)":"92.3"},"paper_url":"https://arxiv.org/abs/2210.11694v2","paper_title":"Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem","paper_date":"2022-10-21","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94930,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"Exp-Tree","metrics":{"Accuracy (%)":"92.3"},"paper_url":"https://arxiv.org/abs/2310.09619v3","paper_title":"An Expression Tree Decoding Strategy for Mathematical Equation Generation","paper_date":"2023-10-14","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94931,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"ATHENA (roberta-base)","metrics":{"Accuracy (%)":"92.2"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94932,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"Roberta-DeductReasoner","metrics":{"Accuracy (%)":"92"},"paper_url":"https://arxiv.org/abs/2203.10316v4","paper_title":"Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction","paper_date":"2022-03-19","code_links":[{"title":"allanj/deductive-mwp","url":"https://github.com/allanj/deductive-mwp"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94933,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"DeBERTa (PM + VM)","metrics":{"Accuracy (%)":"91.0"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94934,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"EPT","metrics":{"Accuracy (%)":"88.7"},"paper_url":"https://aclanthology.org/2022.acl-long.305","paper_title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","paper_date":null,"code_links":[{"title":"snucclab/ept-x","url":"https://github.com/snucclab/ept-x"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94935,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"Graph2Tree with RoBERTa","metrics":{"Accuracy (%)":"88.7"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94936,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"GTS with RoBERTa","metrics":{"Accuracy (%)":"88.5"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94937,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"GEO","metrics":{"Accuracy (%)":"85.1"},"paper_url":"https://aclanthology.org/2020.coling-main.38","paper_title":"Generating Equation by Utilizing Operators : GEO model","paper_date":"2020-12-01","code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94938,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"EPT-X","metrics":{"Accuracy (%)":"84.57"},"paper_url":"https://aclanthology.org/2022.acl-long.305","paper_title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","paper_date":null,"code_links":[{"title":"snucclab/ept-x","url":"https://github.com/snucclab/ept-x"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94939,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"EPT","metrics":{"Accuracy (%)":"84.51"},"paper_url":"https://aclanthology.org/2020.emnlp-main.308","paper_title":"Point to the Expression: Solving Algebraic Word Problems using the Expression-Pointer Transformer Model","paper_date":null,"code_links":[{"title":"snucclab/EPT","url":"https://github.com/snucclab/EPT"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94940,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"Graph2Tree","metrics":{"Accuracy (%)":"83.7"},"paper_url":"https://aclanthology.org/2020.acl-main.362","paper_title":"Graph-to-Tree Learning for Solving Math Word Problems","paper_date":"2020-07-01","code_links":[{"title":"2003pro/Graph2Tree","url":"https://github.com/2003pro/Graph2Tree"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94941,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"LLaMA 2-Chat","metrics":{"Accuracy (%)":"82.4"},"paper_url":"https://arxiv.org/abs/2307.09288v2","paper_title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","paper_date":"2023-07-18","code_links":[{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"Lightning-AI/lit-gpt","url":"https://github.com/Lightning-AI/lit-gpt"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"IBM/Dromedary","url":"https://github.com/IBM/Dromedary"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"xverse-ai/xverse-13b","url":"https://github.com/xverse-ai/xverse-13b"},{"title":"usyd-fsalab/fp6_llm","url":"https://github.com/usyd-fsalab/fp6_llm"},{"title":"rijgersberg/geitje","url":"https://github.com/rijgersberg/geitje"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"glb400/Toy-RecLM","url":"https://github.com/glb400/Toy-RecLM"},{"title":"ninglab/ecellm","url":"https://github.com/ninglab/ecellm"},{"title":"zurichnlp/contradecode","url":"https://github.com/zurichnlp/contradecode"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"idiap/abroad-re","url":"https://github.com/idiap/abroad-re"},{"title":"meetyou-ai-lab/can-mc-evaluate-llms","url":"https://github.com/meetyou-ai-lab/can-mc-evaluate-llms"},{"title":"xuetianci/pacit","url":"https://github.com/xuetianci/pacit"},{"title":"coastalcph/eu-politics-llms","url":"https://github.com/coastalcph/eu-politics-llms"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94942,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"GPT-3.5 turbo (175B)","metrics":{"Accuracy (%)":"80.3"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94943,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"Toolformer","metrics":{"Accuracy (%)":"44.0"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94944,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"GPT-3 (175B)","metrics":{"Accuracy (%)":"19.8"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94945,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"Toolformer (disabled)","metrics":{"Accuracy (%)":"15.0"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94946,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"GPT-J","metrics":{"Accuracy (%)":"9.9"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94947,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"GPT-J + CC","metrics":{"Accuracy (%)":"9.3"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94948,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"OPT (66B)","metrics":{"Accuracy (%)":"7.9"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94949,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"GPT-3 text-curie-001 (13B)","metrics":{"Accuracy (%)":"4.09"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94950,"task":"Math Word Problem Solving","parent_task":null,"dataset":"MAWPS","model_name":"GPT-3 text-babbage-001 (6.7B)","metrics":{"Accuracy (%)":"2.76"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112172,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Accuracy (%)":"95.7"},"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 (%)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112173,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"MsAT-DeductReasoner","metrics":{"Accuracy (%)":"94.3"},"paper_url":"https://arxiv.org/abs/2306.01707v3","paper_title":"Learning Multi-Step Reasoning by Solving Arithmetic Tasks","paper_date":"2023-06-02","code_links":[{"title":"TianduoWang/MsAT","url":"https://github.com/TianduoWang/MsAT"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112174,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"ATHENA (roberta-large)","metrics":{"Accuracy (%)":"93"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112175,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Multi-view","metrics":{"Accuracy (%)":"92.3"},"paper_url":"https://arxiv.org/abs/2210.11694v2","paper_title":"Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem","paper_date":"2022-10-21","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112176,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Exp-Tree","metrics":{"Accuracy (%)":"92.3"},"paper_url":"https://arxiv.org/abs/2310.09619v3","paper_title":"An Expression Tree Decoding Strategy for Mathematical Equation Generation","paper_date":"2023-10-14","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112177,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"ATHENA (roberta-base)","metrics":{"Accuracy (%)":"92.2"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112178,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Roberta-DeductReasoner","metrics":{"Accuracy (%)":"92"},"paper_url":"https://arxiv.org/abs/2203.10316v4","paper_title":"Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction","paper_date":"2022-03-19","code_links":[{"title":"allanj/deductive-mwp","url":"https://github.com/allanj/deductive-mwp"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112179,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"DeBERTa (PM + VM)","metrics":{"Accuracy (%)":"91.0"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112180,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"EPT","metrics":{"Accuracy (%)":"88.7"},"paper_url":"https://aclanthology.org/2022.acl-long.305","paper_title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","paper_date":null,"code_links":[{"title":"snucclab/ept-x","url":"https://github.com/snucclab/ept-x"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112181,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Graph2Tree with RoBERTa","metrics":{"Accuracy (%)":"88.7"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112182,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GTS with RoBERTa","metrics":{"Accuracy (%)":"88.5"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112183,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GEO","metrics":{"Accuracy (%)":"85.1"},"paper_url":"https://aclanthology.org/2020.coling-main.38","paper_title":"Generating Equation by Utilizing Operators : GEO model","paper_date":"2020-12-01","code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112184,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"EPT-X","metrics":{"Accuracy (%)":"84.57"},"paper_url":"https://aclanthology.org/2022.acl-long.305","paper_title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","paper_date":null,"code_links":[{"title":"snucclab/ept-x","url":"https://github.com/snucclab/ept-x"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112185,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"EPT","metrics":{"Accuracy (%)":"84.51"},"paper_url":"https://aclanthology.org/2020.emnlp-main.308","paper_title":"Point to the Expression: Solving Algebraic Word Problems using the Expression-Pointer Transformer Model","paper_date":null,"code_links":[{"title":"snucclab/EPT","url":"https://github.com/snucclab/EPT"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112186,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Graph2Tree","metrics":{"Accuracy (%)":"83.7"},"paper_url":"https://aclanthology.org/2020.acl-main.362","paper_title":"Graph-to-Tree Learning for Solving Math Word Problems","paper_date":"2020-07-01","code_links":[{"title":"2003pro/Graph2Tree","url":"https://github.com/2003pro/Graph2Tree"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112187,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"LLaMA 2-Chat","metrics":{"Accuracy (%)":"82.4"},"paper_url":"https://arxiv.org/abs/2307.09288v2","paper_title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","paper_date":"2023-07-18","code_links":[{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"Lightning-AI/lit-gpt","url":"https://github.com/Lightning-AI/lit-gpt"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"IBM/Dromedary","url":"https://github.com/IBM/Dromedary"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"xverse-ai/xverse-13b","url":"https://github.com/xverse-ai/xverse-13b"},{"title":"usyd-fsalab/fp6_llm","url":"https://github.com/usyd-fsalab/fp6_llm"},{"title":"rijgersberg/geitje","url":"https://github.com/rijgersberg/geitje"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"glb400/Toy-RecLM","url":"https://github.com/glb400/Toy-RecLM"},{"title":"ninglab/ecellm","url":"https://github.com/ninglab/ecellm"},{"title":"zurichnlp/contradecode","url":"https://github.com/zurichnlp/contradecode"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"idiap/abroad-re","url":"https://github.com/idiap/abroad-re"},{"title":"meetyou-ai-lab/can-mc-evaluate-llms","url":"https://github.com/meetyou-ai-lab/can-mc-evaluate-llms"},{"title":"xuetianci/pacit","url":"https://github.com/xuetianci/pacit"},{"title":"coastalcph/eu-politics-llms","url":"https://github.com/coastalcph/eu-politics-llms"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112188,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GPT-3.5 turbo (175B)","metrics":{"Accuracy (%)":"80.3"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112189,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Toolformer","metrics":{"Accuracy (%)":"44.0"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112190,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GPT-3 (175B)","metrics":{"Accuracy (%)":"19.8"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112191,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"Toolformer (disabled)","metrics":{"Accuracy (%)":"15.0"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112192,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GPT-J","metrics":{"Accuracy (%)":"9.9"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112193,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GPT-J + CC","metrics":{"Accuracy (%)":"9.3"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112194,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"OPT (66B)","metrics":{"Accuracy (%)":"7.9"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112195,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GPT-3 text-curie-001 (13B)","metrics":{"Accuracy (%)":"4.09"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112196,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"MAWPS","model_name":"GPT-3 text-babbage-001 (6.7B)","metrics":{"Accuracy (%)":"2.76"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120521,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Accuracy (%)":"95.7"},"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 (%)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120522,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"MsAT-DeductReasoner","metrics":{"Accuracy (%)":"94.3"},"paper_url":"https://arxiv.org/abs/2306.01707v3","paper_title":"Learning Multi-Step Reasoning by Solving Arithmetic Tasks","paper_date":"2023-06-02","code_links":[{"title":"TianduoWang/MsAT","url":"https://github.com/TianduoWang/MsAT"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120523,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"ATHENA (roberta-large)","metrics":{"Accuracy (%)":"93"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120524,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"Multi-view","metrics":{"Accuracy (%)":"92.3"},"paper_url":"https://arxiv.org/abs/2210.11694v2","paper_title":"Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem","paper_date":"2022-10-21","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120525,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"Exp-Tree","metrics":{"Accuracy (%)":"92.3"},"paper_url":"https://arxiv.org/abs/2310.09619v3","paper_title":"An Expression Tree Decoding Strategy for Mathematical Equation Generation","paper_date":"2023-10-14","code_links":[{"title":"zwq2018/multi-view-consistency-for-mwp","url":"https://github.com/zwq2018/multi-view-consistency-for-mwp"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120526,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"ATHENA (roberta-base)","metrics":{"Accuracy (%)":"92.2"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120527,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"Roberta-DeductReasoner","metrics":{"Accuracy (%)":"92"},"paper_url":"https://arxiv.org/abs/2203.10316v4","paper_title":"Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction","paper_date":"2022-03-19","code_links":[{"title":"allanj/deductive-mwp","url":"https://github.com/allanj/deductive-mwp"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120528,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"DeBERTa (PM + VM)","metrics":{"Accuracy (%)":"91.0"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120529,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"EPT","metrics":{"Accuracy (%)":"88.7"},"paper_url":"https://aclanthology.org/2022.acl-long.305","paper_title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","paper_date":null,"code_links":[{"title":"snucclab/ept-x","url":"https://github.com/snucclab/ept-x"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120530,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"Graph2Tree with RoBERTa","metrics":{"Accuracy (%)":"88.7"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120531,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"GTS with RoBERTa","metrics":{"Accuracy (%)":"88.5"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120532,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"GEO","metrics":{"Accuracy (%)":"85.1"},"paper_url":"https://aclanthology.org/2020.coling-main.38","paper_title":"Generating Equation by Utilizing Operators : GEO model","paper_date":"2020-12-01","code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120533,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"EPT-X","metrics":{"Accuracy (%)":"84.57"},"paper_url":"https://aclanthology.org/2022.acl-long.305","paper_title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","paper_date":null,"code_links":[{"title":"snucclab/ept-x","url":"https://github.com/snucclab/ept-x"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120534,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"EPT","metrics":{"Accuracy (%)":"84.51"},"paper_url":"https://aclanthology.org/2020.emnlp-main.308","paper_title":"Point to the Expression: Solving Algebraic Word Problems using the Expression-Pointer Transformer Model","paper_date":null,"code_links":[{"title":"snucclab/EPT","url":"https://github.com/snucclab/EPT"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120535,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"Graph2Tree","metrics":{"Accuracy (%)":"83.7"},"paper_url":"https://aclanthology.org/2020.acl-main.362","paper_title":"Graph-to-Tree Learning for Solving Math Word Problems","paper_date":"2020-07-01","code_links":[{"title":"2003pro/Graph2Tree","url":"https://github.com/2003pro/Graph2Tree"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120536,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"LLaMA 2-Chat","metrics":{"Accuracy (%)":"82.4"},"paper_url":"https://arxiv.org/abs/2307.09288v2","paper_title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","paper_date":"2023-07-18","code_links":[{"title":"facebookresearch/llama","url":"https://github.com/facebookresearch/llama"},{"title":"llamafamily/llama-chinese","url":"https://github.com/llamafamily/llama-chinese"},{"title":"flagalpha/llama2-chinese","url":"https://github.com/flagalpha/llama2-chinese"},{"title":"Lightning-AI/lit-gpt","url":"https://github.com/Lightning-AI/lit-gpt"},{"title":"young-geng/easylm","url":"https://github.com/young-geng/easylm"},{"title":"IBM/Dromedary","url":"https://github.com/IBM/Dromedary"},{"title":"squeezeailab/squeezellm","url":"https://github.com/squeezeailab/squeezellm"},{"title":"xverse-ai/xverse-13b","url":"https://github.com/xverse-ai/xverse-13b"},{"title":"usyd-fsalab/fp6_llm","url":"https://github.com/usyd-fsalab/fp6_llm"},{"title":"rijgersberg/geitje","url":"https://github.com/rijgersberg/geitje"},{"title":"xzhang97666/alpacare","url":"https://github.com/xzhang97666/alpacare"},{"title":"glb400/Toy-RecLM","url":"https://github.com/glb400/Toy-RecLM"},{"title":"ninglab/ecellm","url":"https://github.com/ninglab/ecellm"},{"title":"zurichnlp/contradecode","url":"https://github.com/zurichnlp/contradecode"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"idiap/abroad-re","url":"https://github.com/idiap/abroad-re"},{"title":"meetyou-ai-lab/can-mc-evaluate-llms","url":"https://github.com/meetyou-ai-lab/can-mc-evaluate-llms"},{"title":"xuetianci/pacit","url":"https://github.com/xuetianci/pacit"},{"title":"coastalcph/eu-politics-llms","url":"https://github.com/coastalcph/eu-politics-llms"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120537,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"GPT-3.5 turbo (175B)","metrics":{"Accuracy (%)":"80.3"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120538,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"Toolformer","metrics":{"Accuracy (%)":"44.0"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120539,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"GPT-3 (175B)","metrics":{"Accuracy (%)":"19.8"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120540,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"Toolformer (disabled)","metrics":{"Accuracy (%)":"15.0"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120541,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"GPT-J","metrics":{"Accuracy (%)":"9.9"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120542,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"GPT-J + CC","metrics":{"Accuracy (%)":"9.3"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120543,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"OPT (66B)","metrics":{"Accuracy (%)":"7.9"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120544,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"GPT-3 text-curie-001 (13B)","metrics":{"Accuracy (%)":"4.09"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120545,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"MAWPS","model_name":"GPT-3 text-babbage-001 (6.7B)","metrics":{"Accuracy (%)":"2.76"},"paper_url":"https://arxiv.org/abs/2306.13899v1","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_date":"2023-06-24","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"metrics_order":"[\"Accuracy (%)\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]}]}