{"task":"Code Generation","dataset":"LiveCodeBench","metric_names":["Pass@1"],"rows":[{"id":760509,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 3 Pro Preview (High) (Google)","metrics":{"Pass@1":"91.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760640,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 3 Flash Preview (Reasoning) (Google)","metrics":{"Pass@1":"90.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762200,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek V3.2 Speciale (DeepSeek)","metrics":{"Pass@1":"89.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760611,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5.2 (Medium) (OpenAI)","metrics":{"Pass@1":"89.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761173,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GLM-4.7 (Reasoning) (Z AI)","metrics":{"Pass@1":"89.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760335,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5.2 (Xhigh) (OpenAI)","metrics":{"Pass@1":"88.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762846,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"gpt-oss-120b (High) (OpenAI)","metrics":{"Pass@1":"87.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760436,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude Opus 4.5 (Reasoning) (Anthropic)","metrics":{"Pass@1":"87.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760837,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5.1 (High) (OpenAI)","metrics":{"Pass@1":"86.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761322,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"MiMo-V2-Flash (Reasoning) (Xiaomi)","metrics":{"Pass@1":"86.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761244,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek V3.2 (Reasoning) (DeepSeek)","metrics":{"Pass@1":"86.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761850,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"o4-mini (High) (OpenAI)","metrics":{"Pass@1":"85.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761161,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 3 Pro Preview (Low) (Google)","metrics":{"Pass@1":"85.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761197,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Kimi K2 Thinking (Kimi)","metrics":{"Pass@1":"85.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760951,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5.1 Codex (High) (OpenAI)","metrics":{"Pass@1":"84.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761028,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5 (High) (OpenAI)","metrics":{"Pass@1":"84.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760797,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5 Codex (High) (OpenAI)","metrics":{"Pass@1":"84"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761822,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5 mini (High) (OpenAI)","metrics":{"Pass@1":"83.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761424,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5.1 Codex mini (High) (OpenAI)","metrics":{"Pass@1":"83.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761690,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Grok 4 Fast (Reasoning) (SpaceXAI)","metrics":{"Pass@1":"83.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761605,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"MiniMax-M2 (MiniMax)","metrics":{"Pass@1":"82.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761436,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Grok 4.1 Fast (Reasoning) (SpaceXAI)","metrics":{"Pass@1":"82.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761133,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Grok 4 (SpaceXAI)","metrics":{"Pass@1":"81.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762224,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"ERNIE 5.0 Thinking Preview (Baidu)","metrics":{"Pass@1":"81.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761302,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"MiniMax-M2.1 (MiniMax)","metrics":{"Pass@1":"81"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759135,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DreamPRM-Code","metrics":{"Pass@1":"80.9"},"paper_url":"https://paperswithcode.com/paper/dreamprm-code-function-as-step-process-reward-model-with-label-correction-for-llm-coding","paper_title":"DreamPRM-Code: Function-as-Step Process Reward Model with Label Correction for LLM Coding","paper_date":"2025-12-17","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":761452,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"o3 (OpenAI)","metrics":{"Pass@1":"80.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762407,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Apriel-v1.6-15B-Thinker (ServiceNow)","metrics":{"Pass@1":"80.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761929,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Pro (Google)","metrics":{"Pass@1":"80.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762144,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek V3.1 Terminus (Reasoning) (DeepSeek)","metrics":{"Pass@1":"79.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761702,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 3 Flash Preview (Non-reasoning) (Google)","metrics":{"Pass@1":"79.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761905,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek V3.2 Exp (Reasoning) (DeepSeek)","metrics":{"Pass@1":"78.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762518,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5 nano (High) (OpenAI)","metrics":{"Pass@1":"78.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762590,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 235B A22B 2507 (Reasoning) (Alibaba)","metrics":{"Pass@1":"78.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762383,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek V3.1 (Reasoning) (DeepSeek)","metrics":{"Pass@1":"78.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762971,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 Next 80B A3B (Reasoning) (Alibaba)","metrics":{"Pass@1":"78.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762107,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Pro Preview (Mar' 25) (Google)","metrics":{"Pass@1":"77.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763126,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"INTELLECT-3 (Based on GLM-4.5-Air) (Prime Intellect)","metrics":{"Pass@1":"77.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763651,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"gpt-oss-20b (High) (OpenAI)","metrics":{"Pass@1":"77.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762192,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Pro Preview (May' 25) (Google)","metrics":{"Pass@1":"77"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762492,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek R1 0528 (May '25) (DeepSeek)","metrics":{"Pass@1":"77"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762211,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"K-EXAONE (Reasoning) (LG AI Research)","metrics":{"Pass@1":"76.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-31","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761979,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 Max (Alibaba)","metrics":{"Pass@1":"76.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761795,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Doubao Seed Code (ByteDance Seed)","metrics":{"Pass@1":"76.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762720,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Seed-OSS-36B-Instruct (ByteDance Seed)","metrics":{"Pass@1":"76.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761334,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5 (Low) (OpenAI)","metrics":{"Pass@1":"76.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762644,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5 nano (Medium) (OpenAI)","metrics":{"Pass@1":"76.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762770,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Magistral Medium 1.2 (Mistral)","metrics":{"Pass@1":"75"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761617,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"KAT-Coder-Pro V1 (KwaiKAT)","metrics":{"Pass@1":"74.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764011,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"EXAONE 4.0 32B (Reasoning) (LG AI Research)","metrics":{"Pass@1":"74.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763722,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) (NVIDIA)","metrics":{"Pass@1":"74.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760963,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude Opus 4.5 (Non-reasoning) (Anthropic)","metrics":{"Pass@1":"73.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762565,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GLM-4.5 (Reasoning) (Z AI)","metrics":{"Pass@1":"73.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762758,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 VL 32B (Reasoning) (Alibaba)","metrics":{"Pass@1":"73.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763613,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama Nemotron Super 49B v1.5 (Reasoning) (NVIDIA)","metrics":{"Pass@1":"73.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763070,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"o3-mini (High) (OpenAI)","metrics":{"Pass@1":"73.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-31","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762264,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova 2.0 Pro Preview (Medium) (Amazon)","metrics":{"Pass@1":"73"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762336,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Apriel-v1.5-15B-Thinker (ServiceNow)","metrics":{"Pass@1":"72.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764168,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Falcon-H1R-7B (TII UAE)","metrics":{"Pass@1":"72.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-01-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764457,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"NVIDIA Nemotron Nano 9B V2 (Reasoning) (NVIDIA)","metrics":{"Pass@1":"72.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763837,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Magistral Small 1.2 (Mistral)","metrics":{"Pass@1":"72.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762664,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"o3-mini (OpenAI)","metrics":{"Pass@1":"71.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-31","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761367,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 4.5 Sonnet (Reasoning) (Anthropic)","metrics":{"Pass@1":"71.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762024,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Flash Preview (Sep '25) (Reasoning) (Google)","metrics":{"Pass@1":"71.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762417,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova 2.0 Lite (High) (Amazon)","metrics":{"Pass@1":"71.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762809,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"MiniMax M1 80k (MiniMax)","metrics":{"Pass@1":"71.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763186,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"gpt-oss-120b (Low) (OpenAI)","metrics":{"Pass@1":"70.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763330,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 30B A3B 2507 (Reasoning) (Alibaba)","metrics":{"Pass@1":"70.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761064,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5 (Medium) (OpenAI)","metrics":{"Pass@1":"70.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764846,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"NVIDIA Nemotron Nano 9B V2 (Non-reasoning) (NVIDIA)","metrics":{"Pass@1":"70.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763445,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 VL 30B A3B (Reasoning) (Alibaba)","metrics":{"Pass@1":"69.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762171,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Grok 3 mini Reasoning (High) (SpaceXAI)","metrics":{"Pass@1":"69.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-02-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761630,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GLM-4.6 (Reasoning) (Z AI)","metrics":{"Pass@1":"69.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762505,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Flash (Reasoning) (Google)","metrics":{"Pass@1":"69.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764673,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Olmo 3.1 32B Think (Allen Institute for AI)","metrics":{"Pass@1":"69.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763306,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"K2-V2 (High) (Institute of Foundation Models)","metrics":{"Pass@1":"69.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764429,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"NVIDIA Nemotron Nano 12B v2 VL (Reasoning) (NVIDIA)","metrics":{"Pass@1":"69.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761396,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5 mini (Medium) (OpenAI)","metrics":{"Pass@1":"69.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763164,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) (Google)","metrics":{"Pass@1":"68.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766146,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Cogito v2.1 (Reasoning) (Deep Cogito)","metrics":{"Pass@1":"68.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759282,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"CWM","metrics":{"Pass@1":"68.6"},"paper_url":"https://paperswithcode.com/paper/cwm-an-open-weights-llm-for-research-on-code-generation-with-world-models","paper_title":"CWM: An Open-Weights LLM for Research on Code Generation with World Models","paper_date":"2025-09-30","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":764405,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Hermes 4 - Llama-3.1 405B (Reasoning) (Nous Research)","metrics":{"Pass@1":"68.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763017,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GLM-4.5-Air (Z AI)","metrics":{"Pass@1":"68.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763381,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 Next 80B A3B Instruct (Alibaba)","metrics":{"Pass@1":"68.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762083,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"o1 (OpenAI)","metrics":{"Pass@1":"67.9"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764228,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 Omni 30B A3B (Reasoning) (Alibaba)","metrics":{"Pass@1":"67.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763538,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Ling-1T (InclusionAI)","metrics":{"Pass@1":"67.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-08","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765066,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Olmo 3 32B Think (Allen Institute for AI)","metrics":{"Pass@1":"67.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761774,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5.2 (Non-reasoning) (OpenAI)","metrics":{"Pass@1":"66.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762632,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova 2.0 Lite (Medium) (Amazon)","metrics":{"Pass@1":"66.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762371,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova 2.0 Omni (Medium) (Amazon)","metrics":{"Pass@1":"66"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762278,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Grok Code Fast 1 (SpaceXAI)","metrics":{"Pass@1":"65.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763234,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"MiniMax M1 40k (MiniMax)","metrics":{"Pass@1":"65.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763059,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mi:dm K 2.5 Pro (Korea Telecom)","metrics":{"Pass@1":"65.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761575,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 4 Sonnet (Reasoning) (Anthropic)","metrics":{"Pass@1":"65.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761077,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 4.1 Opus (Reasoning) (Anthropic)","metrics":{"Pass@1":"65.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764110,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Hermes 4 - Llama-3.1 70B (Reasoning) (Nous Research)","metrics":{"Pass@1":"65.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763259,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"gpt-oss-20b (Low) (OpenAI)","metrics":{"Pass@1":"65.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762620,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 Max (Preview) (Alibaba)","metrics":{"Pass@1":"65.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763512,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Motif-2-12.7B-Reasoning (Motif Technologies)","metrics":{"Pass@1":"65.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762395,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 VL 235B A22B (Reasoning) (Alibaba)","metrics":{"Pass@1":"64.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763086,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Ring-1T (InclusionAI)","metrics":{"Pass@1":"64.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763472,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) (Google)","metrics":{"Pass@1":"64.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763738,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 4B 2507 (Reasoning) (Alibaba)","metrics":{"Pass@1":"64.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764369,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) (NVIDIA)","metrics":{"Pass@1":"64.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762551,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova 2.0 Pro Preview (Low) (Amazon)","metrics":{"Pass@1":"63.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761383,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 4 Opus (Reasoning) (Anthropic)","metrics":{"Pass@1":"63.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763434,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"QwQ 32B (Alibaba)","metrics":{"Pass@1":"63.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762915,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"HyperCLOVA X SEED Think (32B) (Naver)","metrics":{"Pass@1":"62.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764651,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Ring-flash-2.0 (InclusionAI)","metrics":{"Pass@1":"62.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762684,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) (Google)","metrics":{"Pass@1":"62.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763421,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 235B A22B (Reasoning) (Alibaba)","metrics":{"Pass@1":"62.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762890,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek R1 (Jan '25) (DeepSeek)","metrics":{"Pass@1":"61.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765473,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Olmo 3 7B Think (Allen Institute for AI)","metrics":{"Pass@1":"61.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764417,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Solar Pro 2 (Reasoning) (Upstage)","metrics":{"Pass@1":"61.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761806,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 4.5 Haiku (Reasoning) (Anthropic)","metrics":{"Pass@1":"61.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762047,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Kimi K2 0905 (Kimi)","metrics":{"Pass@1":"61"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764331,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GLM-4.5V (Reasoning) (Z AI)","metrics":{"Pass@1":"60.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763271,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 VL 235B A22B Instruct (Alibaba)","metrics":{"Pass@1":"59.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761959,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek V3.2 (Non-reasoning) (DeepSeek)","metrics":{"Pass@1":"59.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763869,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Flash-Lite (Reasoning) (Google)","metrics":{"Pass@1":"59.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763005,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova 2.0 Omni (Low) (Amazon)","metrics":{"Pass@1":"59.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761546,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 4.5 Sonnet (Non-reasoning) (Anthropic)","metrics":{"Pass@1":"59"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764207,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Ling-flash-2.0 (InclusionAI)","metrics":{"Pass@1":"58.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762745,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 Coder 480B A35B Instruct (Alibaba)","metrics":{"Pass@1":"58.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762359,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek V3.1 (Non-reasoning) (DeepSeek)","metrics":{"Pass@1":"57.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763347,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"o1-mini (OpenAI)","metrics":{"Pass@1":"57.6"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766157,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mi:dm K 2.5 Pro Preview (Korea Telecom)","metrics":{"Pass@1":"57.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761746,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GLM-4.7 (Non-reasoning) (Z AI)","metrics":{"Pass@1":"56.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762115,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GLM-4.6 (Non-reasoning) (Z AI)","metrics":{"Pass@1":"56.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762878,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5 (Minimal) (OpenAI)","metrics":{"Pass@1":"55.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762577,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Kimi K2 (Kimi)","metrics":{"Pass@1":"55.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762324,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek V3.2 Exp (Non-reasoning) (DeepSeek)","metrics":{"Pass@1":"55.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":758961,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Embarrassingly Simple Self-Distillation ","metrics":{"Pass@1":"55.3"},"paper_url":"https://paperswithcode.com/paper/embarrassingly-simple-self-distillation-improves-code-generation","paper_title":"Embarrassingly Simple Self-Distillation Improves Code Generation","paper_date":"2026-04-01","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":763852,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 32B (Reasoning) (Alibaba)","metrics":{"Pass@1":"54.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764469,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Hermes 4 - Llama-3.1 405B (Non-reasoning) (Nous Research)","metrics":{"Pass@1":"54.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763294,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5 mini (Minimal) (OpenAI)","metrics":{"Pass@1":"54.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763145,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5 (ChatGPT) (OpenAI)","metrics":{"Pass@1":"54.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761883,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 4 Opus (Non-reasoning) (Anthropic)","metrics":{"Pass@1":"54.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763602,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"K2-V2 (Medium) (Institute of Foundation Models)","metrics":{"Pass@1":"54.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761917,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 Max Thinking (Preview) (Alibaba)","metrics":{"Pass@1":"53.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762301,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek V3.1 Terminus (Non-reasoning) (DeepSeek)","metrics":{"Pass@1":"52.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763577,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Magistral Medium 1 (Mistral)","metrics":{"Pass@1":"52.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762732,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 235B A22B 2507 Instruct (Alibaba)","metrics":{"Pass@1":"52.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764034,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 14B (Reasoning) (Alibaba)","metrics":{"Pass@1":"52.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765691,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Exaone 4.0 1.2B (Reasoning) (LG AI Research)","metrics":{"Pass@1":"51.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764380,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 30B A3B 2507 Instruct (Alibaba)","metrics":{"Pass@1":"51.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763929,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 VL 32B Instruct (Alibaba)","metrics":{"Pass@1":"51.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763992,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Magistral Small 1 (Mistral)","metrics":{"Pass@1":"51.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764063,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek R1 0528 Qwen3 8B (DeepSeek)","metrics":{"Pass@1":"51.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762035,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 4.5 Haiku (Non-reasoning) (Anthropic)","metrics":{"Pass@1":"51.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764292,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 30B A3B (Reasoning) (Alibaba)","metrics":{"Pass@1":"50.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762839,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Flash Preview (Reasoning) (Google)","metrics":{"Pass@1":"50.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763317,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Flash (Non-reasoning) (Google)","metrics":{"Pass@1":"49.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762431,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5.1 (Non-reasoning) (OpenAI)","metrics":{"Pass@1":"49.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764537,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) (NVIDIA)","metrics":{"Pass@1":"49.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763201,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-4.1 mini (OpenAI)","metrics":{"Pass@1":"48.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764099,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 VL 30B A3B Instruct (Alibaba)","metrics":{"Pass@1":"47.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761725,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 3.7 Sonnet (Reasoning) (Anthropic)","metrics":{"Pass@1":"47.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-02-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763245,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova 2.0 Pro Preview (Non-reasoning) (Amazon)","metrics":{"Pass@1":"47.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765141,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"EXAONE 4.0 32B (Non-reasoning) (LG AI Research)","metrics":{"Pass@1":"47.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764708,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-5 nano (Minimal) (OpenAI)","metrics":{"Pass@1":"47"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762787,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova 2.0 Lite (Low) (Amazon)","metrics":{"Pass@1":"46.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764393,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"ERNIE 4.5 300B A47B (Baidu)","metrics":{"Pass@1":"46.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763484,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral Large 3 (Mistral)","metrics":{"Pass@1":"46.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764611,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 4B (Reasoning) (Alibaba)","metrics":{"Pass@1":"46.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763561,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Solar Pro 2 (Preview) (Reasoning) (Upstage)","metrics":{"Pass@1":"46.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762607,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-4.1 (OpenAI)","metrics":{"Pass@1":"45.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761893,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 4 Sonnet (Non-reasoning) (Anthropic)","metrics":{"Pass@1":"44.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763822,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Devstral 2 (Mistral)","metrics":{"Pass@1":"44.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765460,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Reka Flash 3 (Reka AI)","metrics":{"Pass@1":"43.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765524,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Ling-mini-2.0 (InclusionAI)","metrics":{"Pass@1":"42.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762707,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Grok 3 (SpaceXAI)","metrics":{"Pass@1":"42.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-02-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763667,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-4o (March 2025, chatgpt-4o-latest) (OpenAI)","metrics":{"Pass@1":"42.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764746,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Solar Pro 2 (Non-reasoning) (Upstage)","metrics":{"Pass@1":"42.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765231,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 Omni 30B A3B Instruct (Alibaba)","metrics":{"Pass@1":"42.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763950,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GLM-4.6V (Non-reasoning) (Z AI)","metrics":{"Pass@1":"41.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-08","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763523,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral Medium 3.1 (Mistral)","metrics":{"Pass@1":"40.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763815,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Flash Preview (Non-reasoning) (Google)","metrics":{"Pass@1":"40.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764571,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 8B (Reasoning) (Alibaba)","metrics":{"Pass@1":"40.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763354,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek V3 0324 (DeepSeek)","metrics":{"Pass@1":"40.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763400,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 Coder 30B A3B Instruct (Alibaba)","metrics":{"Pass@1":"40.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-31","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761946,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"MiMo-V2-Flash (Non-reasoning) (Xiaomi)","metrics":{"Pass@1":"40.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763039,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Grok 4 Fast (Non-reasoning) (SpaceXAI)","metrics":{"Pass@1":"40.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763589,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral Medium 3 (Mistral)","metrics":{"Pass@1":"40"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764931,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.5 Flash-Lite (Non-reasoning) (Google)","metrics":{"Pass@1":"40"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762926,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Grok 4.1 Fast (Non-reasoning) (SpaceXAI)","metrics":{"Pass@1":"39.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763217,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 4 Maverick (Meta)","metrics":{"Pass@1":"39.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762059,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 3.7 Sonnet (Non-reasoning) (Anthropic)","metrics":{"Pass@1":"39.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-02-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764526,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"K2-V2 (Low) (Institute of Foundation Models)","metrics":{"Pass@1":"39.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764129,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Solar Pro 2 (Preview) (Non-reasoning) (Upstage)","metrics":{"Pass@1":"38.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764149,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 3.5 Sonnet (Oct '24) (Anthropic)","metrics":{"Pass@1":"38.1"},"paper_url":null,"paper_title":null,"paper_date":"2024-10-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764548,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Kimi Linear 48B A3B Instruct (Kimi)","metrics":{"Pass@1":"37.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764869,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 4B 2507 Instruct (Alibaba)","metrics":{"Pass@1":"37.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764158,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek R1 Distill Qwen 14B (DeepSeek)","metrics":{"Pass@1":"37.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764834,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) (NVIDIA)","metrics":{"Pass@1":"36"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763882,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek V3 (Dec '24) (DeepSeek)","metrics":{"Pass@1":"35.9"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764092,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen2.5 Max (Alibaba)","metrics":{"Pass@1":"35.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764022,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 VL 8B (Reasoning) (Alibaba)","metrics":{"Pass@1":"35.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764907,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GLM-4.5V (Non-reasoning) (Z AI)","metrics":{"Pass@1":"35.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765207,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Ministral 3 14B (Mistral)","metrics":{"Pass@1":"35.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764354,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Devstral Small 2 (Mistral)","metrics":{"Pass@1":"34.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763764,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.0 Pro Experimental (Feb '25) (Google)","metrics":{"Pass@1":"34.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-02-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763772,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova 2.0 Lite (Non-reasoning) (Amazon)","metrics":{"Pass@1":"34.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765360,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) (NVIDIA)","metrics":{"Pass@1":"34.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763962,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 235B A22B (Non-reasoning) (Alibaba)","metrics":{"Pass@1":"34.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763624,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Devstral Medium (Mistral)","metrics":{"Pass@1":"33.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764324,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"QwQ 32B-Preview (Alibaba)","metrics":{"Pass@1":"33.7"},"paper_url":null,"paper_title":null,"paper_date":"2024-11-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763675,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.0 Flash (Feb '25) (Google)","metrics":{"Pass@1":"33.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-02-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764511,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-4o (May '24) (OpenAI)","metrics":{"Pass@1":"33.4"},"paper_url":null,"paper_title":null,"paper_date":"2024-05-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764599,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 VL 8B Instruct (Alibaba)","metrics":{"Pass@1":"33.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764179,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-4.1 nano (OpenAI)","metrics":{"Pass@1":"32.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764981,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 30B A3B (Non-reasoning) (Alibaba)","metrics":{"Pass@1":"32.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763456,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.0 Flash Thinking Experimental (Jan '25) (Google)","metrics":{"Pass@1":"32.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764727,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 VL 4B (Reasoning) (Alibaba)","metrics":{"Pass@1":"32"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763549,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova Premier (Amazon)","metrics":{"Pass@1":"31.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764239,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-4o (Aug '24) (OpenAI)","metrics":{"Pass@1":"31.7"},"paper_url":null,"paper_title":null,"paper_date":"2024-08-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764121,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 1.5 Pro (Sep '24) (Google)","metrics":{"Pass@1":"31.6"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763687,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 3.5 Haiku (Anthropic)","metrics":{"Pass@1":"31.4"},"paper_url":null,"paper_title":null,"paper_date":"2024-10-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763899,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-4o (Nov '24) (OpenAI)","metrics":{"Pass@1":"30.9"},"paper_url":null,"paper_title":null,"paper_date":"2024-11-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765781,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 1.7B (Reasoning) (Alibaba)","metrics":{"Pass@1":"30.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764051,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova 2.0 Omni (Non-reasoning) (Amazon)","metrics":{"Pass@1":"30.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764559,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.1 Instruct 405B (Meta)","metrics":{"Pass@1":"30.5"},"paper_url":null,"paper_title":null,"paper_date":"2024-07-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765571,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Ministral 3 8B (Mistral)","metrics":{"Pass@1":"30.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764075,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 4 Scout (Meta)","metrics":{"Pass@1":"29.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764263,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Sonar (Perplexity)","metrics":{"Pass@1":"29.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764880,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen2.5 Coder Instruct 32B (Alibaba)","metrics":{"Pass@1":"29.5"},"paper_url":null,"paper_title":null,"paper_date":"2024-11-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765644,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Sarvam M (Reasoning, Based on Mistral Small 3.1) (Sarvam)","metrics":{"Pass@1":"29.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764343,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral Large 2 (Nov '24) (Mistral)","metrics":{"Pass@1":"29.3"},"paper_url":null,"paper_title":null,"paper_date":"2024-11-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765714,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Exaone 4.0 1.2B (Non-reasoning) (LG AI Research)","metrics":{"Pass@1":"29.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764637,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.1 Tulu3 405B (Allen Institute for AI)","metrics":{"Pass@1":"29.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764737,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-4 Turbo (OpenAI)","metrics":{"Pass@1":"29.1"},"paper_url":null,"paper_title":null,"paper_date":"2023-11-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764488,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama Nemotron Super 49B v1.5 (Non-reasoning) (NVIDIA)","metrics":{"Pass@1":"29"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765447,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 VL 4B Instruct (Alibaba)","metrics":{"Pass@1":"29"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764277,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.3 Instruct 70B (Meta)","metrics":{"Pass@1":"28.8"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764500,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 32B (Non-reasoning) (Alibaba)","metrics":{"Pass@1":"28.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764771,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Command A (Cohere)","metrics":{"Pass@1":"28.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764588,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) (NVIDIA)","metrics":{"Pass@1":"28"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764887,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 14B (Non-reasoning) (Alibaba)","metrics":{"Pass@1":"28"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763795,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 3 Opus (Anthropic)","metrics":{"Pass@1":"27.9"},"paper_url":null,"paper_title":null,"paper_date":"2024-03-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763700,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.3 Nemotron Super 49B v1 (Reasoning) (NVIDIA)","metrics":{"Pass@1":"27.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764251,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen2.5 Instruct 72B (Alibaba)","metrics":{"Pass@1":"27.6"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763975,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral Small 3.2 (Mistral)","metrics":{"Pass@1":"27.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764305,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Sonar Pro (Perplexity)","metrics":{"Pass@1":"27.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764720,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 1.5 Flash (Sep '24) (Google)","metrics":{"Pass@1":"27.3"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763940,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek R1 Distill Qwen 32B (DeepSeek)","metrics":{"Pass@1":"27"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764970,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Hermes 4 - Llama-3.1 70B (Non-reasoning) (Nous Research)","metrics":{"Pass@1":"26.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764701,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Grok 2 (Dec '24) (SpaceXAI)","metrics":{"Pass@1":"26.7"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764858,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral Large 2 (Jul '24) (Mistral)","metrics":{"Pass@1":"26.7"},"paper_url":null,"paper_title":null,"paper_date":"2024-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764136,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek R1 Distill Llama 70B (DeepSeek)","metrics":{"Pass@1":"26.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765702,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Olmo 3 7B Instruct (Allen Institute for AI)","metrics":{"Pass@1":"26.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764663,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Pixtral Large (Mistral)","metrics":{"Pass@1":"26.1"},"paper_url":null,"paper_title":null,"paper_date":"2024-11-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763784,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Devstral Small (May '25) (Mistral)","metrics":{"Pass@1":"25.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764312,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Devstral Small (Jul '25) (Mistral)","metrics":{"Pass@1":"25.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764919,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral Small 3 (Mistral)","metrics":{"Pass@1":"25.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765195,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Granite 4.0 H Small (IBM)","metrics":{"Pass@1":"25.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764827,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen2.5 Instruct 32B (Alibaba)","metrics":{"Pass@1":"24.8"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765941,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Ministral 3 3B (Mistral)","metrics":{"Pass@1":"24.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765077,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 1.5 Pro (May '24) (Google)","metrics":{"Pass@1":"24.4"},"paper_url":null,"paper_title":null,"paper_date":"2024-05-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764820,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Grok Beta (SpaceXAI)","metrics":{"Pass@1":"24.1"},"paper_url":null,"paper_title":null,"paper_date":"2024-08-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764957,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GPT-4o mini (OpenAI)","metrics":{"Pass@1":"23.4"},"paper_url":null,"paper_title":null,"paper_date":"2024-07-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764758,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova Pro (Amazon)","metrics":{"Pass@1":"23.3"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764998,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 4B (Non-reasoning) (Alibaba)","metrics":{"Pass@1":"23.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765049,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek R1 Distill Llama 8B (DeepSeek)","metrics":{"Pass@1":"23.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765005,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.1 Instruct 70B (Meta)","metrics":{"Pass@1":"23.2"},"paper_url":null,"paper_title":null,"paper_date":"2024-07-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765298,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Phi-4 (Microsoft)","metrics":{"Pass@1":"23.1"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765161,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 1.5 Flash-8B (Google)","metrics":{"Pass@1":"21.7"},"paper_url":null,"paper_title":null,"paper_date":"2024-10-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759328,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Dream-Coder","metrics":{"Pass@1":"21.4"},"paper_url":"https://paperswithcode.com/paper/dream-coder-7b-an-open-diffusion-language-model-for-code","paper_title":"Dream-Coder 7B: An Open Diffusion Language Model for Code","paper_date":"2025-09-01","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":765098,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.2 Instruct 90B (Vision) (Meta)","metrics":{"Pass@1":"21.4"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764684,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral Small 3.1 (Mistral)","metrics":{"Pass@1":"21.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764004,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.0 Flash (experimental) (Google)","metrics":{"Pass@1":"21"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765436,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Jamba Reasoning 3B (AI21 Labs)","metrics":{"Pass@1":"21"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-08","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765251,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 8B (Non-reasoning) (Alibaba)","metrics":{"Pass@1":"20.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765587,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3 Instruct 70B (Meta)","metrics":{"Pass@1":"19.8"},"paper_url":null,"paper_title":null,"paper_date":"2024-04-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765291,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 1.5 Flash (May '24) (Google)","metrics":{"Pass@1":"19.6"},"paper_url":null,"paper_title":null,"paper_date":"2024-05-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765176,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepHermes 3 - Mistral 24B Preview (Non-reasoning) (Nous Research)","metrics":{"Pass@1":"19.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765484,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 2.1 (Anthropic)","metrics":{"Pass@1":"19.5"},"paper_url":null,"paper_title":null,"paper_date":"2023-11-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765243,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Hermes 3 - Llama-3.1 70B (Nous Research)","metrics":{"Pass@1":"18.8"},"paper_url":null,"paper_title":null,"paper_date":"2024-08-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764481,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.0 Flash-Lite (Feb '25) (Google)","metrics":{"Pass@1":"18.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-02-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765183,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Jamba 1.7 Large (AI21 Labs)","metrics":{"Pass@1":"18.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765827,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Granite 4.0 Micro (IBM)","metrics":{"Pass@1":"18"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764519,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 2.0 Flash-Lite (Preview) (Google)","metrics":{"Pass@1":"17.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-02-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765393,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral Large (Feb '24) (Mistral)","metrics":{"Pass@1":"17.8"},"paper_url":null,"paper_title":null,"paper_date":"2024-02-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765311,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 3 Sonnet (Anthropic)","metrics":{"Pass@1":"17.5"},"paper_url":null,"paper_title":null,"paper_date":"2024-03-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765277,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Jamba 1.6 Large (AI21 Labs)","metrics":{"Pass@1":"17.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765543,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 2.0 (Anthropic)","metrics":{"Pass@1":"17.1"},"paper_url":null,"paper_title":null,"paper_date":"2023-07-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764793,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.1 Nemotron Instruct 70B (NVIDIA)","metrics":{"Pass@1":"16.9"},"paper_url":null,"paper_title":null,"paper_date":"2024-10-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764944,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova Lite (Amazon)","metrics":{"Pass@1":"16.7"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765087,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen2.5 Turbo (Alibaba)","metrics":{"Pass@1":"16.3"},"paper_url":null,"paper_title":null,"paper_date":"2024-11-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762949,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"GLM-4.6V (Reasoning) (Z AI)","metrics":{"Pass@1":"16"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-08","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765120,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen2 Instruct 72B (Alibaba)","metrics":{"Pass@1":"15.9"},"paper_url":null,"paper_title":null,"paper_date":"2024-06-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765639,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek Coder V2 Lite Instruct (DeepSeek)","metrics":{"Pass@1":"15.8"},"paper_url":null,"paper_title":null,"paper_date":"2024-06-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765491,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude 3 Haiku (Anthropic)","metrics":{"Pass@1":"15.4"},"paper_url":null,"paper_title":null,"paper_date":"2024-03-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765891,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"LFM2 8B A1B (Liquid AI)","metrics":{"Pass@1":"15.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765401,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mixtral 8x22B Instruct (Mistral)","metrics":{"Pass@1":"14.8"},"paper_url":null,"paper_title":null,"paper_date":"2024-04-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766004,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemma 3n E4B Instruct (Google)","metrics":{"Pass@1":"14.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765223,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Jamba 1.5 Large (AI21 Labs)","metrics":{"Pass@1":"14.3"},"paper_url":null,"paper_title":null,"paper_date":"2024-08-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765340,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral Small (Sep '24) (Mistral)","metrics":{"Pass@1":"14.1"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765318,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Nova Micro (Amazon)","metrics":{"Pass@1":"14"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765372,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemma 3n E4B Instruct Preview (May '25) (Google)","metrics":{"Pass@1":"13.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765925,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemma 3 27B Instruct (Google)","metrics":{"Pass@1":"13.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766122,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemma 3 12B Instruct (Google)","metrics":{"Pass@1":"13.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765379,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Phi-4 Multimodal Instruct (Microsoft)","metrics":{"Pass@1":"13.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-02-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765901,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Granite 3.3 8B (Non-reasoning) (IBM)","metrics":{"Pass@1":"12.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765127,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Phi-4 Mini Instruct (Microsoft)","metrics":{"Pass@1":"12.6"},"paper_url":null,"paper_title":null,"paper_date":"2024-02-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765386,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen2.5 Coder Instruct 7B (Alibaba)","metrics":{"Pass@1":"12.6"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765913,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 1.7B (Non-reasoning) (Alibaba)","metrics":{"Pass@1":"12.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765670,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Command-R+ (Apr '24) (Cohere)","metrics":{"Pass@1":"12.2"},"paper_url":null,"paper_title":null,"paper_date":"2024-04-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766093,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 0.6B (Reasoning) (Alibaba)","metrics":{"Pass@1":"12.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764805,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.1 Instruct 8B (Meta)","metrics":{"Pass@1":"11.6"},"paper_url":null,"paper_title":null,"paper_date":"2024-07-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765349,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Phi-3 Mini Instruct 3.8B (Microsoft)","metrics":{"Pass@1":"11.6"},"paper_url":null,"paper_title":null,"paper_date":"2024-04-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765632,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemini 1.0 Pro (Google)","metrics":{"Pass@1":"11.6"},"paper_url":null,"paper_title":null,"paper_date":"2023-12-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765677,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"OpenChat 3.5 (1210) (OpenChat)","metrics":{"Pass@1":"11.5"},"paper_url":null,"paper_title":null,"paper_date":"2023-12-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765770,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Granite 4.0 H 1B (IBM)","metrics":{"Pass@1":"11.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765977,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemma 3 4B Instruct (Google)","metrics":{"Pass@1":"11.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765551,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral Small (Feb '24) (Mistral)","metrics":{"Pass@1":"11.1"},"paper_url":null,"paper_title":null,"paper_date":"2024-02-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765608,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.2 Instruct 11B (Vision) (Meta)","metrics":{"Pass@1":"11"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765845,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Claude Instant (Anthropic)","metrics":{"Pass@1":"10.9"},"paper_url":null,"paper_title":null,"paper_date":"2023-03-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765558,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral Medium (Mistral)","metrics":{"Pass@1":"9.9"},"paper_url":null,"paper_title":null,"paper_date":"2023-12-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765656,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 2 Chat 70B (Meta)","metrics":{"Pass@1":"9.8"},"paper_url":null,"paper_title":null,"paper_date":"2023-07-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765663,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 2 Chat 13B (Meta)","metrics":{"Pass@1":"9.8"},"paper_url":null,"paper_title":null,"paper_date":"2023-07-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765601,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"LFM 40B (Liquid AI)","metrics":{"Pass@1":"9.6"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766058,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3 Instruct 8B (Meta)","metrics":{"Pass@1":"9.6"},"paper_url":null,"paper_title":null,"paper_date":"2024-04-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765992,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemma 3n E2B Instruct (Google)","metrics":{"Pass@1":"9.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765684,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DBRX Instruct (Databricks)","metrics":{"Pass@1":"9.3"},"paper_url":null,"paper_title":null,"paper_date":"2024-03-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765838,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) (Nous Research)","metrics":{"Pass@1":"8.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-02-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765416,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.2 Instruct 3B (Meta)","metrics":{"Pass@1":"8.3"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759165,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"ThinkMerge","metrics":{"Pass@1":"8.28"},"paper_url":"https://paperswithcode.com/paper/think-in-parallel-answer-as-one-logit-averaging-for-open-ended-reasoning","paper_title":"Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning","paper_date":"2025-12-02","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":765744,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"LFM2 2.6B (Liquid AI)","metrics":{"Pass@1":"8.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766081,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Qwen3 0.6B (Non-reasoning) (Alibaba)","metrics":{"Pass@1":"7.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765793,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Jamba 1.6 Mini (AI21 Labs)","metrics":{"Pass@1":"7.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765534,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DeepSeek R1 Distill Qwen 1.5B (DeepSeek)","metrics":{"Pass@1":"7"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765266,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"OLMo 2 32B (Allen Institute for AI)","metrics":{"Pass@1":"6.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765800,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mixtral 8x7B Instruct (Mistral)","metrics":{"Pass@1":"6.6"},"paper_url":null,"paper_title":null,"paper_date":"2023-12-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":758879,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"DuST","metrics":{"Pass@1":"6.2"},"paper_url":"https://paperswithcode.com/paper/primal-generation-dual-judgment-self-training-from-test-time-scaling","paper_title":"Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling","paper_date":"2026-05-11","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":759072,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Bridging Online and Offline RL: Contextu","metrics":{"Pass@1":"6.2"},"paper_url":"https://paperswithcode.com/paper/bridging-online-and-offline-rl-contextual-bandit-learning-for-multi-turn-code-generation","paper_title":"Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation","paper_date":"2026-02-03","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":765762,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Jamba 1.5 Mini (AI21 Labs)","metrics":{"Pass@1":"6.2"},"paper_url":null,"paper_title":null,"paper_date":"2024-08-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765732,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Jamba 1.7 Mini (AI21 Labs)","metrics":{"Pass@1":"6.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765853,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Command-R (Mar '24) (Cohere)","metrics":{"Pass@1":"4.8"},"paper_url":null,"paper_title":null,"paper_date":"2024-03-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765873,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Granite 4.0 1B (IBM)","metrics":{"Pass@1":"4.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765861,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Mistral 7B Instruct (Mistral)","metrics":{"Pass@1":"4.6"},"paper_url":null,"paper_title":null,"paper_date":"2023-09-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765503,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"OLMo 2 7B (Allen Institute for AI)","metrics":{"Pass@1":"4.1"},"paper_url":null,"paper_title":null,"paper_date":"2024-11-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765514,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Molmo 7B-D (Allen Institute for AI)","metrics":{"Pass@1":"3.9"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766019,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Granite 4.0 350M (IBM)","metrics":{"Pass@1":"2.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766040,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"LFM2 1.2B (Liquid AI)","metrics":{"Pass@1":"2"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766029,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Granite 4.0 H 350M (IBM)","metrics":{"Pass@1":"1.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766070,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 3.2 Instruct 1B (Meta)","metrics":{"Pass@1":"1.9"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765965,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemma 3 1B Instruct (Google)","metrics":{"Pass@1":"1.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765808,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Gemma 3 270M (Google)","metrics":{"Pass@1":"0.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765408,"task":"Code Generation","parent_task":null,"dataset":"LiveCodeBench","model_name":"Llama 2 Chat 7B (Meta)","metrics":{"Pass@1":"0.2"},"paper_url":null,"paper_title":null,"paper_date":"2023-07-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Pass@1\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]}]}