{"task":"Code Generation","dataset":"SciCode","metric_names":["Accuracy"],"rows":[{"id":759427,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Opus 5.5 (Max, Default Fallback) (Anthropic)","metrics":{"Accuracy":"66.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759437,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Opus 5.5 (Xhigh, Default Fallback) (Anthropic)","metrics":{"Accuracy":"65"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759448,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Fable 5.1 (Max, Default Fallback) (Anthropic)","metrics":{"Accuracy":"63.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759474,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 4 Argon (High) (Google)","metrics":{"Accuracy":"61.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759432,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Sonnet 5.5 (Max, Default Fallback) (Anthropic)","metrics":{"Accuracy":"61"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759550,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Fable 5 (Max, Opus 4.8 Fallback) (Anthropic)","metrics":{"Accuracy":"61"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759457,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Fable 5.1 (Xhigh, Default Fallback) (Anthropic)","metrics":{"Accuracy":"60.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759643,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"MiMo-V2.6-Pro (Xiaomi)","metrics":{"Accuracy":"60.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759442,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Opus 5.5 (High, Default Fallback) (Anthropic)","metrics":{"Accuracy":"60.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759898,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 3.7 Flash (Medium) (Google)","metrics":{"Accuracy":"59.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759667,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Muse Spark 1.3 (Xhigh) (Meta)","metrics":{"Accuracy":"59.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759734,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Kimi K3 (Max) (Kimi)","metrics":{"Accuracy":"59.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759498,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Opus 5.5 (Medium, Default Fallback) (Anthropic)","metrics":{"Accuracy":"59.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759685,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GLM-5.3 (Max) (Z AI)","metrics":{"Accuracy":"59"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759728,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Step 5 Preview (StepFun)","metrics":{"Accuracy":"58.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759589,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Muse Spark 1.3 (Max) (Meta)","metrics":{"Accuracy":"58.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760166,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Muse Spark 1.1 (Xhigh) (Meta)","metrics":{"Accuracy":"58.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759504,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Fable 5.1 (High, Default Fallback) (Anthropic)","metrics":{"Accuracy":"58.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760394,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 3.1 Pro Preview (Google)","metrics":{"Accuracy":"58.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759773,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Opus 5.5 (Low, Default Fallback) (Anthropic)","metrics":{"Accuracy":"58.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759638,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Grok 4.7 (High) (SpaceXAI)","metrics":{"Accuracy":"57.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759762,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Sol (High) (OpenAI)","metrics":{"Accuracy":"57.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759602,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Sol (Max) (OpenAI)","metrics":{"Accuracy":"57.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759633,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Grok 4.7 (Xhigh) (SpaceXAI)","metrics":{"Accuracy":"57.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759907,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Muse Spark 1.2 (Xhigh) (Meta)","metrics":{"Accuracy":"57.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759930,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Sol (Medium) (OpenAI)","metrics":{"Accuracy":"57.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759488,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Sonnet 5.5 (Xhigh, Default Fallback) (Anthropic)","metrics":{"Accuracy":"57.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759942,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 3.7 Flash (High) (Google)","metrics":{"Accuracy":"57.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759608,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Sol (Max) (OpenAI)","metrics":{"Accuracy":"57.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759717,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Sol (Xhigh) (OpenAI)","metrics":{"Accuracy":"57.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759620,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Fable 5.1 (Low, Default Fallback) (Anthropic)","metrics":{"Accuracy":"56.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759832,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 3.8 Flash (High) (Google)","metrics":{"Accuracy":"56.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759466,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Astra (Max) (OpenAI)","metrics":{"Accuracy":"56.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759694,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Grok 4.6 (High) (SpaceXAI)","metrics":{"Accuracy":"56.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759527,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Opus 5 (Max) (Anthropic)","metrics":{"Accuracy":"56.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759571,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Fable 5.1 (Medium, Default Fallback) (Anthropic)","metrics":{"Accuracy":"56.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760212,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Sol (Low) (OpenAI)","metrics":{"Accuracy":"56.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760033,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.5 (High) (OpenAI)","metrics":{"Accuracy":"56.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759748,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Grok 4.6 (Medium) (SpaceXAI)","metrics":{"Accuracy":"55.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759535,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6.1 Sol (High) (OpenAI)","metrics":{"Accuracy":"55.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759976,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.5 (Xhigh) (OpenAI)","metrics":{"Accuracy":"55.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759480,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Astra (Xhigh) (OpenAI)","metrics":{"Accuracy":"55.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759512,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6.1 Sol (Xhigh) (OpenAI)","metrics":{"Accuracy":"55.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759541,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Opus 5 (Xhigh) (Anthropic)","metrics":{"Accuracy":"55.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760045,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 3.7 Flash (Low) (Google)","metrics":{"Accuracy":"55.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759518,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Astra (High) (OpenAI)","metrics":{"Accuracy":"55.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759580,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Opus 5 (High) (Anthropic)","metrics":{"Accuracy":"55.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759702,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Sol (Xhigh) (OpenAI)","metrics":{"Accuracy":"55.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759889,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 3.8 Flash (Medium) (Google)","metrics":{"Accuracy":"55.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759742,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Haiku 5.5 (Max) (Anthropic)","metrics":{"Accuracy":"55"},"paper_url":null,"paper_title":null,"paper_date":"2026-10-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759789,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Terra (Max) (OpenAI)","metrics":{"Accuracy":"55"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759962,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Grok 4.5 (High) (SpaceXAI)","metrics":{"Accuracy":"55"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-08","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760224,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 3.8 Flash (Low) (Google)","metrics":{"Accuracy":"55"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759756,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Sol (High) (OpenAI)","metrics":{"Accuracy":"54.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759778,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Grok 4.7 (Low) (SpaceXAI)","metrics":{"Accuracy":"54.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759996,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Luna (Max) (OpenAI)","metrics":{"Accuracy":"54.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760154,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.5 (Medium) (OpenAI)","metrics":{"Accuracy":"54.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759810,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Opus 4.8 (Max) (Anthropic)","metrics":{"Accuracy":"54.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759988,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Sonnet 5 (Max) (Anthropic)","metrics":{"Accuracy":"54.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760280,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Sonnet 5 (High) (Anthropic)","metrics":{"Accuracy":"54.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759493,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6.1 Sol (Max) (OpenAI)","metrics":{"Accuracy":"54.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759562,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Astra (Medium) (OpenAI)","metrics":{"Accuracy":"54.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759970,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Mistral Large 4 Preview (Mistral)","metrics":{"Accuracy":"54.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-10-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759649,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Astra (Low) (OpenAI)","metrics":{"Accuracy":"54.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759826,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Ling 3.1 Flash (InclusionAI)","metrics":{"Accuracy":"54.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-10-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759866,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.8 2.4T A95B (Alibaba)","metrics":{"Accuracy":"54.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760104,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Sonnet 5 (Xhigh) (Anthropic)","metrics":{"Accuracy":"54.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760238,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 3.5 Flash (High) (Google)","metrics":{"Accuracy":"53.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759883,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Sol (Medium) (OpenAI)","metrics":{"Accuracy":"53.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759628,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Sonnet 5.5 (High, Default Fallback) (Anthropic)","metrics":{"Accuracy":"53.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760024,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Luna (Max) (OpenAI)","metrics":{"Accuracy":"53.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760141,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 3.6 Flash (High) (Google)","metrics":{"Accuracy":"53.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759597,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6.1 Sol (Medium) (OpenAI)","metrics":{"Accuracy":"53.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759783,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6.1 Sol (Low) (OpenAI)","metrics":{"Accuracy":"53.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759857,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.8 Max (Alibaba)","metrics":{"Accuracy":"53.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759708,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Grok 4.6 (Xhigh) (SpaceXAI)","metrics":{"Accuracy":"53"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759840,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Sonnet 5.5 (Medium, Default Fallback) (Anthropic)","metrics":{"Accuracy":"52.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760368,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Kimi K3 (Low) (Kimi)","metrics":{"Accuracy":"52.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760673,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.5 Instant (June 2026) (OpenAI)","metrics":{"Accuracy":"52.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760124,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Terra (High) (OpenAI)","metrics":{"Accuracy":"52.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760002,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Terra (Xhigh) (OpenAI)","metrics":{"Accuracy":"52.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759658,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.8 Max (0902) (Alibaba)","metrics":{"Accuracy":"52.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760918,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.4 mini (Xhigh) (OpenAI)","metrics":{"Accuracy":"52.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760149,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"JT-4.1 Flash 236B A21B (Reasoning) (China Mobile)","metrics":{"Accuracy":"52"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759915,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek V4.1 Flash (Max) (DeepSeek)","metrics":{"Accuracy":"51.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759821,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Haiku 5.5 (Xhigh) (Anthropic)","metrics":{"Accuracy":"51.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-10-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760085,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Luna (Xhigh) (OpenAI)","metrics":{"Accuracy":"51.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759801,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GLM 5.3 Flash (Z AI)","metrics":{"Accuracy":"51.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760264,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Luna (High) (OpenAI)","metrics":{"Accuracy":"51.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760502,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Sonnet 5 (Medium) (Anthropic)","metrics":{"Accuracy":"51.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759676,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Opus 5 (Medium) (Anthropic)","metrics":{"Accuracy":"51.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760582,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Kimi K2.6 (Reasoning) (Kimi)","metrics":{"Accuracy":"51.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760013,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"MiMo-V2.6-Flash (Xiaomi)","metrics":{"Accuracy":"51.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760175,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GLM-5.2 (Max) (Z AI)","metrics":{"Accuracy":"51.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760054,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek V4 Pro 0813 (Max) (DeepSeek)","metrics":{"Accuracy":"51"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760388,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Luna (Medium) (OpenAI)","metrics":{"Accuracy":"50.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760322,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek V4 Pro 0424 (Max) (DeepSeek)","metrics":{"Accuracy":"50.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759875,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.8-Flash-Next (Alibaba)","metrics":{"Accuracy":"50.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760682,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"MiMo-V2.5-Pro (Reasoning) (Xiaomi)","metrics":{"Accuracy":"50.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760091,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Luna (Xhigh) (OpenAI)","metrics":{"Accuracy":"50.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760357,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Terra (Medium) (OpenAI)","metrics":{"Accuracy":"50.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760110,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek V4 Flash 0731 (Max) (DeepSeek)","metrics":{"Accuracy":"50.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-31","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760232,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Luna (High) (OpenAI)","metrics":{"Accuracy":"50.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760135,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Sol (Low) (OpenAI)","metrics":{"Accuracy":"50.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760377,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Sonnet 4.6 (Max) (Anthropic)","metrics":{"Accuracy":"50.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760892,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Sonnet 5 (Low) (Anthropic)","metrics":{"Accuracy":"50.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761096,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"MiniMax-M2.7 (MiniMax)","metrics":{"Accuracy":"50.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760545,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Terra (Low) (OpenAI)","metrics":{"Accuracy":"49.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760077,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek V4 Flash Vision (Max) (DeepSeek)","metrics":{"Accuracy":"49.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760706,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Inkling Small (Thinking Machines)","metrics":{"Accuracy":"49.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760406,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.7 Max (Alibaba)","metrics":{"Accuracy":"49.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760068,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Grok 4.6 (Low) (SpaceXAI)","metrics":{"Accuracy":"49.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759921,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Opus 5 (Low) (Anthropic)","metrics":{"Accuracy":"49.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760417,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Haiku 5.5 (Low) (Anthropic)","metrics":{"Accuracy":"49.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-10-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760062,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Sonnet 5.5 (Low, Default Fallback) (Anthropic)","metrics":{"Accuracy":"49.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760099,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Haiku 5.5 (Medium) (Anthropic)","metrics":{"Accuracy":"49"},"paper_url":null,"paper_title":null,"paper_date":"2026-10-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760018,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude Haiku 5.5 (High) (Anthropic)","metrics":{"Accuracy":"48.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-10-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760730,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Hy3 (Tencent)","metrics":{"Accuracy":"48.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760808,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Grok 4.3 (High) (SpaceXAI)","metrics":{"Accuracy":"48.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760594,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Quasar 438B (Max, Based on GLM-5.2) (Multiverse Computing)","metrics":{"Accuracy":"48.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760828,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Solar Open2 250B (Upstage)","metrics":{"Accuracy":"48"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760694,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Kimi K2.7 Code (Kimi)","metrics":{"Accuracy":"47.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760475,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Sol (Non-reasoning) (OpenAI)","metrics":{"Accuracy":"47.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760929,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Solar Mini 4 (Upstage)","metrics":{"Accuracy":"47.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760453,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Sol (Non-reasoning) (OpenAI)","metrics":{"Accuracy":"47.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761354,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.4 nano (Xhigh) (OpenAI)","metrics":{"Accuracy":"47.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760423,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"MiniMax-M3 (MiniMax)","metrics":{"Accuracy":"47.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760787,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Inkling (Xhigh) (Thinking Machines)","metrics":{"Accuracy":"47"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761237,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Luna (Low) (OpenAI)","metrics":{"Accuracy":"46.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760778,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Luna (Medium) (OpenAI)","metrics":{"Accuracy":"46.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760187,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.8 27B (Xhigh) (Alibaba)","metrics":{"Accuracy":"46.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761930,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 2.5 Pro (Google)","metrics":{"Accuracy":"46.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760759,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.7 Plus (Alibaba)","metrics":{"Accuracy":"46.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761292,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Luna (Low) (OpenAI)","metrics":{"Accuracy":"46.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761368,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude 4.5 Sonnet (Reasoning) (Anthropic)","metrics":{"Accuracy":"45.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760622,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Apodex 1.1 (Apodex)","metrics":{"Accuracy":"45.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762159,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemma 4 31B (Reasoning) (Google)","metrics":{"Accuracy":"45.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760906,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek V4 Flash 0420 (Max) (DeepSeek)","metrics":{"Accuracy":"45.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761345,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Terra (Non-reasoning) (OpenAI)","metrics":{"Accuracy":"45.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761862,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Ring-2.6-1T (InclusionAI)","metrics":{"Accuracy":"45"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-08","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761736,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Muse Glimmer (High) (Meta)","metrics":{"Accuracy":"44.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760661,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GLM-5.1 (Reasoning) (Z AI)","metrics":{"Accuracy":"44.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761649,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.5 397B A17B (Reasoning) (Alibaba)","metrics":{"Accuracy":"44.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760494,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Solar Pro 4 (Upstage)","metrics":{"Accuracy":"44.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760864,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Ling-3.0-flash-VL (InclusionAI)","metrics":{"Accuracy":"44.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760747,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"MiMo-V2.5 (Xiaomi)","metrics":{"Accuracy":"43.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761517,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Step 3.7 Flash (StepFun)","metrics":{"Accuracy":"43.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762002,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 3.1 Flash-Lite (Google)","metrics":{"Accuracy":"43.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760484,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Nex-N2-Pro (Based on Qwen3.5-397B-A17B) (Nex AGI)","metrics":{"Accuracy":"43.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761643,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-6 Luna (Non-reasoning) (OpenAI)","metrics":{"Accuracy":"43.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760314,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"K2 Horizon 375B A23B (Institute of Foundation Models)","metrics":{"Accuracy":"42.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761273,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.6 27B (Reasoning) (Alibaba)","metrics":{"Accuracy":"42.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763071,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"o3-mini (High) (OpenAI)","metrics":{"Accuracy":"42.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-31","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761123,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Ling-3.0-flash-Fin (InclusionAI)","metrics":{"Accuracy":"42.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760204,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Motif 3 (Motif Technologies)","metrics":{"Accuracy":"42.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761807,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Claude 4.5 Haiku (Reasoning) (Anthropic)","metrics":{"Accuracy":"42.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760118,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GLM-5.3 (Low) (Z AI)","metrics":{"Accuracy":"42"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761473,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Ling 3.0 Flash (InclusionAI)","metrics":{"Accuracy":"42"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761509,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"K-EXAONE 2.0 0803 (LG AI Research)","metrics":{"Accuracy":"42"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762591,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3 235B A22B 2507 (Reasoning) (Alibaba)","metrics":{"Accuracy":"41.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761187,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemini 3.5 Flash-Lite (Google)","metrics":{"Accuracy":"41.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761257,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"A.X-K2 (SK Telecom)","metrics":{"Accuracy":"41"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763102,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Trinity Large Thinking (Arcee AI)","metrics":{"Accuracy":"40.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762014,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5.6 Luna (Non-reasoning) (OpenAI)","metrics":{"Accuracy":"40.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761043,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Nemotron 3 Ultra 550B A55B (Reasoning) (NVIDIA)","metrics":{"Accuracy":"40.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760873,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek V4 Flash 0420 (High) (DeepSeek)","metrics":{"Accuracy":"40.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762241,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Mistral Medium 3.5 (Mistral)","metrics":{"Accuracy":"40.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760652,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.8 27B (Low) (Alibaba)","metrics":{"Accuracy":"40"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760723,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"K2 Horizon MoVA 36B A4B (Institute of Foundation Models)","metrics":{"Accuracy":"40"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761837,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemma 4 26B A4B (Reasoning) (Google)","metrics":{"Accuracy":"40"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761445,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek V4 Pro 0813 (Non-reasoning) (DeepSeek)","metrics":{"Accuracy":"39.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761990,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.5 122B A10B (Reasoning) (Alibaba)","metrics":{"Accuracy":"39.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762288,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Grok 4.3 (Non-reasoning) (SpaceXAI)","metrics":{"Accuracy":"39.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760536,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.8 27B (Medium) (Alibaba)","metrics":{"Accuracy":"39"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761823,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"GPT-5 mini (High) (OpenAI)","metrics":{"Accuracy":"39"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763355,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek V3 0324 (DeepSeek)","metrics":{"Accuracy":"39"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763652,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"gpt-oss-20b (High) (OpenAI)","metrics":{"Accuracy":"38.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762936,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Mistral Small 4 (Reasoning) (Mistral)","metrics":{"Accuracy":"38.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763282,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"North Mini Code (Cohere)","metrics":{"Accuracy":"38.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762461,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Command A+ (Cohere)","metrics":{"Accuracy":"38.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762693,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Mercury 2.5 (Inception)","metrics":{"Accuracy":"38.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-08","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762891,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek R1 (Jan '25) (DeepSeek)","metrics":{"Accuracy":"38.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762145,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek V3.1 Terminus (Reasoning) (DeepSeek)","metrics":{"Accuracy":"38"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762134,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Granite 4.2 30B (IBM)","metrics":{"Accuracy":"37.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762346,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Mercury 2 (Inception)","metrics":{"Accuracy":"37.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761211,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"G9v3-39A5B (AI9Stars)","metrics":{"Accuracy":"36.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761669,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.6 35B A3B (Reasoning) (Alibaba)","metrics":{"Accuracy":"36.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763485,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Mistral Large 3 (Mistral)","metrics":{"Accuracy":"36.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761565,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"LongCat 2.0 (LongCat)","metrics":{"Accuracy":"36.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761464,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.8 27B (Non-reasoning) (Alibaba)","metrics":{"Accuracy":"36.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762538,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Nemotron 3 Super 120B A12B (Reasoning) (NVIDIA)","metrics":{"Accuracy":"36.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763499,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3 Coder Next (Alibaba)","metrics":{"Accuracy":"36.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763853,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3 32B (Reasoning) (Alibaba)","metrics":{"Accuracy":"36"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763883,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek V3 (Dec '24) (DeepSeek)","metrics":{"Accuracy":"35.8"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760858,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"DeepSeek V4.1 Flash (Non-reasoning) (DeepSeek)","metrics":{"Accuracy":"35.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762847,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"gpt-oss-120b (High) (OpenAI)","metrics":{"Accuracy":"34"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763331,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3 30B A3B 2507 (Reasoning) (Alibaba)","metrics":{"Accuracy":"33"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763823,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Devstral 2 (Mistral)","metrics":{"Accuracy":"32.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763524,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Mistral Medium 3.1 (Mistral)","metrics":{"Accuracy":"32.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764355,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Devstral Small 2 (Mistral)","metrics":{"Accuracy":"32.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762529,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Nemotron 3.5 Lightning (NVIDIA)","metrics":{"Accuracy":"32.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763218,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Llama 4 Maverick (Meta)","metrics":{"Accuracy":"31.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763029,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Granite 4.2 8B (IBM)","metrics":{"Accuracy":"31.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764035,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3 14B (Reasoning) (Alibaba)","metrics":{"Accuracy":"30.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763723,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) (NVIDIA)","metrics":{"Accuracy":"30.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762985,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3.5 9B (Reasoning) (Alibaba)","metrics":{"Accuracy":"29.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763976,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Mistral Small 3.2 (Mistral)","metrics":{"Accuracy":"28.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764572,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Qwen3 8B (Reasoning) (Alibaba)","metrics":{"Accuracy":"27.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764685,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Mistral Small 3.1 (Mistral)","metrics":{"Accuracy":"27.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761407,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"K2 Horizon 7B (Institute of Foundation Models)","metrics":{"Accuracy":"27.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762673,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"MiniCPM5-2B (OpenBMB)","metrics":{"Accuracy":"26.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764194,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Solar Pro 3 (Upstage)","metrics":{"Accuracy":"25.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763567,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Granite 4.2 3B (IBM)","metrics":{"Accuracy":"25.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763711,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemma 4 E4B (Reasoning) (Google)","metrics":{"Accuracy":"24.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763050,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Ling 3.0 Tiny (InclusionAI)","metrics":{"Accuracy":"24.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765208,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Ministral 3 14B (Mistral)","metrics":{"Accuracy":"23.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765926,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemma 3 27B Instruct (Google)","metrics":{"Accuracy":"23.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761970,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"K2 Horizon 3.7B (Institute of Foundation Models)","metrics":{"Accuracy":"22"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765109,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Celeris-1 (Celeris)","metrics":{"Accuracy":"21.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764076,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Llama 4 Scout (Meta)","metrics":{"Accuracy":"21.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765572,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Ministral 3 8B (Mistral)","metrics":{"Accuracy":"20.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766123,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Gemma 3 12B Instruct (Google)","metrics":{"Accuracy":"16.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766111,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"NVIDIA Nemotron 3 Nano 4B (NVIDIA)","metrics":{"Accuracy":"16.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765942,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"Ministral 3 3B (Mistral)","metrics":{"Accuracy":"15.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763920,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"LFM2.5-2.6B (Liquid AI)","metrics":{"Accuracy":"14.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766137,"task":"Code Generation","parent_task":null,"dataset":"SciCode","model_name":"K2 Horizon 0.9B (Institute of Foundation Models)","metrics":{"Accuracy":"6.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]}]}