{"task":"Language Modelling","dataset":"Artificial Analysis Coding Index","metric_names":["Index"],"rows":[{"id":759453,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Fable 5.1 (Max, Default Fallback) (Anthropic)","metrics":{"Index":"81.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759462,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Fable 5.1 (Xhigh, Default Fallback) (Anthropic)","metrics":{"Index":"80.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759509,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Fable 5.1 (High, Default Fallback) (Anthropic)","metrics":{"Index":"79.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759725,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Sol (Xhigh) (OpenAI)","metrics":{"Index":"78.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759532,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Opus 5 (Max) (Anthropic)","metrics":{"Index":"78"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759616,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Sol (Max) (OpenAI)","metrics":{"Index":"77.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759770,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Sol (High) (OpenAI)","metrics":{"Index":"77.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759523,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-6 Astra (High) (OpenAI)","metrics":{"Index":"77.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759576,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Fable 5.1 (Medium, Default Fallback) (Anthropic)","metrics":{"Index":"77.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759546,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Opus 5 (Xhigh) (Anthropic)","metrics":{"Index":"77"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759471,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-6 Astra (Max) (OpenAI)","metrics":{"Index":"76.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759699,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Grok 4.6 (High) (SpaceXAI)","metrics":{"Index":"76.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759567,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-6 Astra (Medium) (OpenAI)","metrics":{"Index":"76.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759797,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Terra (Max) (OpenAI)","metrics":{"Index":"76.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759558,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Fable 5 (Max, Opus 4.8 Fallback) (Anthropic)","metrics":{"Index":"76.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759585,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Opus 5 (High) (Anthropic)","metrics":{"Index":"76.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759672,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Muse Spark 1.3 (Xhigh) (Meta)","metrics":{"Index":"76.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759837,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 3.8 Flash (High) (Google)","metrics":{"Index":"76.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759938,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Sol (Medium) (OpenAI)","metrics":{"Index":"76.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759663,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.8 Max (0902) (Alibaba)","metrics":{"Index":"76.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759739,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Kimi K3 (Max) (Kimi)","metrics":{"Index":"76.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759947,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 3.7 Flash (High) (Google)","metrics":{"Index":"76.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759485,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-6 Astra (Xhigh) (OpenAI)","metrics":{"Index":"75.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759713,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Grok 4.6 (Xhigh) (SpaceXAI)","metrics":{"Index":"75.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759594,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Muse Spark 1.3 (Max) (Meta)","metrics":{"Index":"75.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759654,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-6 Astra (Low) (OpenAI)","metrics":{"Index":"75.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759625,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Fable 5.1 (Low, Default Fallback) (Anthropic)","metrics":{"Index":"75.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759984,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.5 (Xhigh) (OpenAI)","metrics":{"Index":"74.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759690,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GLM-5.3 (Max) (Z AI)","metrics":{"Index":"74.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759753,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Grok 4.6 (Medium) (SpaceXAI)","metrics":{"Index":"74.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759681,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Opus 5 (Medium) (Anthropic)","metrics":{"Index":"74.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759818,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Opus 4.8 (Max) (Anthropic)","metrics":{"Index":"74.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759894,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 3.8 Flash (Medium) (Google)","metrics":{"Index":"74.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759853,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Opus 4.7 (Max) (Anthropic)","metrics":{"Index":"73.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760229,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 3.8 Flash (Low) (Google)","metrics":{"Index":"73.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759880,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.8-Flash-Next (Alibaba)","metrics":{"Index":"73.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759967,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Grok 4.5 (High) (SpaceXAI)","metrics":{"Index":"72.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-08","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759912,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Muse Spark 1.2 (Xhigh) (Meta)","metrics":{"Index":"72.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760373,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Kimi K3 (Low) (Kimi)","metrics":{"Index":"72"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759871,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.8 2.4T A95B (Alibaba)","metrics":{"Index":"71.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759862,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.8 Max (Alibaba)","metrics":{"Index":"71.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760041,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.5 (High) (OpenAI)","metrics":{"Index":"71.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759806,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GLM 5.3 Flash (Z AI)","metrics":{"Index":"71.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759903,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 3.7 Flash (Medium) (Google)","metrics":{"Index":"71.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759993,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Sonnet 5 (Max) (Anthropic)","metrics":{"Index":"71.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760162,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.5 (Medium) (OpenAI)","metrics":{"Index":"71.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760029,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Luna (Max) (OpenAI)","metrics":{"Index":"71.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760171,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Muse Spark 1.1 (Xhigh) (Meta)","metrics":{"Index":"71.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759958,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.4 (Xhigh) (OpenAI)","metrics":{"Index":"71.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760050,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 3.7 Flash (Low) (Google)","metrics":{"Index":"71"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760010,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Terra (Xhigh) (OpenAI)","metrics":{"Index":"70.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760246,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 3.5 Flash (High) (Google)","metrics":{"Index":"70.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760220,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Sol (Low) (OpenAI)","metrics":{"Index":"69.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760146,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 3.6 Flash (High) (Google)","metrics":{"Index":"69.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760115,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DeepSeek V4 Flash 0731 (Max) (DeepSeek)","metrics":{"Index":"69.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-31","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760059,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DeepSeek V4 Pro 0813 (Max) (DeepSeek)","metrics":{"Index":"68.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760183,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GLM-5.2 (Max) (Z AI)","metrics":{"Index":"68.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760402,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 3.1 Pro Preview (Google)","metrics":{"Index":"68.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760096,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Luna (Xhigh) (OpenAI)","metrics":{"Index":"68.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760192,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.8 27B (Xhigh) (Alibaba)","metrics":{"Index":"68.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760132,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Terra (High) (OpenAI)","metrics":{"Index":"67.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":759926,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Opus 5 (Low) (Anthropic)","metrics":{"Index":"66.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761012,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Sonnet 5 (Non-reasoning, High) (Anthropic)","metrics":{"Index":"66.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760073,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Grok 4.6 (Low) (SpaceXAI)","metrics":{"Index":"66.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760414,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.7 Max (Alibaba)","metrics":{"Index":"66"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760480,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Sol (Non-reasoning) (OpenAI)","metrics":{"Index":"65.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760082,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DeepSeek V4 Flash Vision (Max) (DeepSeek)","metrics":{"Index":"65"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760364,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Terra (Medium) (OpenAI)","metrics":{"Index":"64.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760209,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Motif 3 (Motif Technologies)","metrics":{"Index":"63.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760269,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Luna (High) (OpenAI)","metrics":{"Index":"63.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760385,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Sonnet 4.6 (Max) (Anthropic)","metrics":{"Index":"63"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760261,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Motif 3 (Beta) (Motif Technologies)","metrics":{"Index":"62"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760590,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Kimi K2.6 (Reasoning) (Kimi)","metrics":{"Index":"61.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760319,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"K2 Horizon 375B A23B (Institute of Foundation Models)","metrics":{"Index":"61.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760599,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Quasar 438B (Max, Based on GLM-5.2) (Multiverse Computing)","metrics":{"Index":"61.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760310,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.5 (Low) (OpenAI)","metrics":{"Index":"60.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760627,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Apodex 1.1 (Apodex)","metrics":{"Index":"60.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760702,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Kimi K2.7 Code (Kimi)","metrics":{"Index":"60.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760690,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"MiMo-V2.5-Pro (Reasoning) (Xiaomi)","metrics":{"Index":"60.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761234,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"KAT Coder Pro V2 (KwaiKAT)","metrics":{"Index":"59.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760330,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DeepSeek V4 Pro 0424 (Max) (DeepSeek)","metrics":{"Index":"59.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760491,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Nex-N2-Pro (Based on Qwen3.5-397B-A17B) (Nex AGI)","metrics":{"Index":"59.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760735,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Hy3 (Tencent)","metrics":{"Index":"58.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760353,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DeepSeek V4 Pro 0424 (High) (DeepSeek)","metrics":{"Index":"58.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760292,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Muse Spark (Meta)","metrics":{"Index":"58.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-08","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760431,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"MiniMax-M3 (MiniMax)","metrics":{"Index":"58.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760657,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.8 27B (Low) (Alibaba)","metrics":{"Index":"58.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760553,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Terra (Low) (OpenAI)","metrics":{"Index":"58.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760869,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Ling-3.0-flash-VL (InclusionAI)","metrics":{"Index":"57"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760755,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"MiMo-V2.5 (Xiaomi)","metrics":{"Index":"56.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761023,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.5 (Non-reasoning) (OpenAI)","metrics":{"Index":"56.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760914,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DeepSeek V4 Flash 0420 (Max) (DeepSeek)","metrics":{"Index":"56.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760541,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.8 27B (Medium) (Alibaba)","metrics":{"Index":"56.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760926,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.4 mini (Xhigh) (OpenAI)","metrics":{"Index":"56.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761362,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.4 nano (Xhigh) (OpenAI)","metrics":{"Index":"56.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760767,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.7 Plus (Alibaba)","metrics":{"Index":"55.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760669,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GLM-5.1 (Reasoning) (Z AI)","metrics":{"Index":"55.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761128,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Ling-3.0-flash-Fin (InclusionAI)","metrics":{"Index":"55.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760578,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.6 Plus (Alibaba)","metrics":{"Index":"54.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761281,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.6 27B (Reasoning) (Alibaba)","metrics":{"Index":"53.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760711,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Inkling Small (Thinking Machines)","metrics":{"Index":"52.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760499,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Solar Pro 4 (Upstage)","metrics":{"Index":"52.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761104,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"MiniMax-M2.7 (MiniMax)","metrics":{"Index":"52.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760560,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"JT-4.1 Flash 236B A21B (Non-reasoning) (China Mobile)","metrics":{"Index":"52.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761350,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Terra (Non-reasoning) (OpenAI)","metrics":{"Index":"52.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760792,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Inkling (Xhigh) (Thinking Machines)","metrics":{"Index":"52.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761377,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude 4.5 Sonnet (Reasoning) (Anthropic)","metrics":{"Index":"52.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760881,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DeepSeek V4 Flash 0420 (High) (DeepSeek)","metrics":{"Index":"52"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760567,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Grok Build 0.1 0616 (SpaceXAI)","metrics":{"Index":"51.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760783,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Luna (Medium) (OpenAI)","metrics":{"Index":"50.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761478,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Ling 3.0 Flash (InclusionAI)","metrics":{"Index":"50.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761954,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"MiMo-V2-Flash (Non-reasoning) (Xiaomi)","metrics":{"Index":"49.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760846,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.1 (High) (OpenAI)","metrics":{"Index":"49.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761051,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Nemotron 3 Ultra 550B A55B (Reasoning) (NVIDIA)","metrics":{"Index":"49.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761192,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 3.5 Flash-Lite (Google)","metrics":{"Index":"49.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761741,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Muse Glimmer (High) (Meta)","metrics":{"Index":"49"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761657,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.5 397B A17B (Reasoning) (Alibaba)","metrics":{"Index":"48.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762249,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Mistral Medium 3.5 (Mistral)","metrics":{"Index":"46.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760996,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Kimi K2.5 (Reasoning) (Kimi)","metrics":{"Index":"46.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-01-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762111,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 2.5 Pro Preview (Mar' 25) (Google)","metrics":{"Index":"46.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761497,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.6 27B (Non-reasoning) (Alibaba)","metrics":{"Index":"46.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761156,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GLM-5.2 (Non-reasoning) (Z AI)","metrics":{"Index":"46.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761639,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GLM-4.6 (Reasoning) (Z AI)","metrics":{"Index":"45.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761998,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.5 122B A10B (Reasoning) (Alibaba)","metrics":{"Index":"45.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761182,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GLM-4.7 (Reasoning) (Z AI)","metrics":{"Index":"45.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761570,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"LongCat 2.0 (LongCat)","metrics":{"Index":"45.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760833,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Solar Open2 250B (Upstage)","metrics":{"Index":"45"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761469,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.8 27B (Non-reasoning) (Alibaba)","metrics":{"Index":"44.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761252,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DeepSeek V3.2 (Reasoning) (DeepSeek)","metrics":{"Index":"44.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761297,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Luna (Low) (OpenAI)","metrics":{"Index":"44.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761816,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude 4.5 Haiku (Reasoning) (Anthropic)","metrics":{"Index":"43.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762154,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DeepSeek V3.1 Terminus (Reasoning) (DeepSeek)","metrics":{"Index":"43.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762167,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemma 4 31B (Reasoning) (Google)","metrics":{"Index":"43.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761720,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.5 122B A10B (Non-reasoning) (Alibaba)","metrics":{"Index":"43.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761870,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Ring-2.6-1T (InclusionAI)","metrics":{"Index":"42.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-08","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760816,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Grok 4.3 (High) (SpaceXAI)","metrics":{"Index":"42.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761677,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.6 35B A3B (Reasoning) (Alibaba)","metrics":{"Index":"41.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761514,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"K-EXAONE 2.0 0803 (LG AI Research)","metrics":{"Index":"40.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762091,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"o1 (OpenAI)","metrics":{"Index":"39.7"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761525,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Step 3.7 Flash (StepFun)","metrics":{"Index":"39.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":760678,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.5 Instant (June 2026) (OpenAI)","metrics":{"Index":"39.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761845,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemma 4 26B A4B (Reasoning) (Google)","metrics":{"Index":"39.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762019,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5.6 Luna (Non-reasoning) (OpenAI)","metrics":{"Index":"39.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761262,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"A.X-K2 (SK Telecom)","metrics":{"Index":"38.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761412,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"K2 Horizon 7B (Institute of Foundation Models)","metrics":{"Index":"38.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761038,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5 (High) (OpenAI)","metrics":{"Index":"37.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762546,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Nemotron 3 Super 120B A12B (Reasoning) (NVIDIA)","metrics":{"Index":"37.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761585,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude 4 Sonnet (Reasoning) (Anthropic)","metrics":{"Index":"37.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-05-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762102,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.5 35B A3B (Non-reasoning) (Alibaba)","metrics":{"Index":"37"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763290,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"North Mini Code (Cohere)","metrics":{"Index":"36.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761732,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude 3.7 Sonnet (Reasoning) (Anthropic)","metrics":{"Index":"36.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-02-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763507,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3 Coder Next (Alibaba)","metrics":{"Index":"36.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762296,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Grok 4.3 (Non-reasoning) (SpaceXAI)","metrics":{"Index":"35.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762010,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 3.1 Flash-Lite (Google)","metrics":{"Index":"34.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762272,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Nova 2.0 Pro Preview (Medium) (Amazon)","metrics":{"Index":"34"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762909,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"o1-preview (OpenAI)","metrics":{"Index":"34"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761940,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 2.5 Pro (Google)","metrics":{"Index":"33.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762319,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemma 4 31B (Non-reasoning) (Google)","metrics":{"Index":"33.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761216,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"G9v3-39A5B (AI9Stars)","metrics":{"Index":"33.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762219,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"K-EXAONE (Reasoning) (LG AI Research)","metrics":{"Index":"32.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-31","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763832,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Devstral 2 (Mistral)","metrics":{"Index":"31.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762354,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Mercury 2 (Inception)","metrics":{"Index":"31.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762259,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemma 4 12B (Reasoning) (Google)","metrics":{"Index":"31"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762856,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"gpt-oss-120b (High) (OpenAI)","metrics":{"Index":"30.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764153,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude 3.5 Sonnet (Oct '24) (Anthropic)","metrics":{"Index":"30.2"},"paper_url":null,"paper_title":null,"paper_date":"2024-10-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762139,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Granite 4.2 30B (IBM)","metrics":{"Index":"29.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764364,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Devstral Small 2 (Mistral)","metrics":{"Index":"29.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762993,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.5 9B (Reasoning) (Alibaba)","metrics":{"Index":"28.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762078,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.6 35B A3B (Non-reasoning) (Alibaba)","metrics":{"Index":"28.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762469,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Command A+ (Cohere)","metrics":{"Index":"27.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762534,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Nemotron 3.5 Lightning (NVIDIA)","metrics":{"Index":"26.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762944,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Mistral Small 4 (Reasoning) (Mistral)","metrics":{"Index":"26.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763055,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Ling 3.0 Tiny (InclusionAI)","metrics":{"Index":"26.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764695,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Mistral Small 3.1 (Mistral)","metrics":{"Index":"26.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761975,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"K2 Horizon 3.7B (Institute of Foundation Models)","metrics":{"Index":"26.1"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764632,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude 3.5 Sonnet (June '24) (Anthropic)","metrics":{"Index":"26"},"paper_url":null,"paper_title":null,"paper_date":"2024-06-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762559,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Nova 2.0 Pro Preview (Low) (Amazon)","metrics":{"Index":"25.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763110,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Trinity Large Thinking (Arcee AI)","metrics":{"Index":"25.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-01","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763768,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 2.0 Pro Experimental (Feb '25) (Google)","metrics":{"Index":"25.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-02-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762835,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Nemotron Cascade 2 30B A3B (NVIDIA)","metrics":{"Index":"25.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-19","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763377,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Ling 2.6 Flash (InclusionAI)","metrics":{"Index":"25.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762901,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DeepSeek R1 (Jan '25) (DeepSeek)","metrics":{"Index":"24.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764515,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-4o (May '24) (OpenAI)","metrics":{"Index":"24.2"},"paper_url":null,"paper_title":null,"paper_date":"2024-05-13","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763460,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 2.0 Flash Thinking Experimental (Jan '25) (Google)","metrics":{"Index":"24.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762458,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"EXAONE 4.5 33B (Reasoning) (LG AI Research)","metrics":{"Index":"23.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-09","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764125,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 1.5 Pro (Sep '24) (Google)","metrics":{"Index":"23.6"},"paper_url":null,"paper_title":null,"paper_date":"2024-09-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762448,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.5 9B (Non-reasoning) (Alibaba)","metrics":{"Index":"23.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762805,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"HyperNova 60B 2605 (High, Based on gpt-oss-120b) (Multiverse Computing)","metrics":{"Index":"23.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762425,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Nova 2.0 Lite (High) (Amazon)","metrics":{"Index":"23"},"paper_url":null,"paper_title":null,"paper_date":"2025-10-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763893,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DeepSeek V3 (Dec '24) (DeepSeek)","metrics":{"Index":"23"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762487,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.5 4B (Reasoning) (Alibaba)","metrics":{"Index":"22.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763034,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Granite 4.2 8B (IBM)","metrics":{"Index":"22.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762601,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3 235B A22B 2507 (Reasoning) (Alibaba)","metrics":{"Index":"22.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764741,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-4 Turbo (OpenAI)","metrics":{"Index":"21.5"},"paper_url":null,"paper_title":null,"paper_date":"2023-11-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762779,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Magistral Medium 1.2 (Mistral)","metrics":{"Index":"21.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763195,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"gpt-oss-120b (Low) (OpenAI)","metrics":{"Index":"21.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763365,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DeepSeek V3 0324 (DeepSeek)","metrics":{"Index":"21.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762867,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"K2 Think V2 (Institute of Foundation Models)","metrics":{"Index":"21"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763253,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Nova 2.0 Pro Preview (Non-reasoning) (Amazon)","metrics":{"Index":"20.9"},"paper_url":null,"paper_title":null,"paper_date":"2025-11-27","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763661,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"gpt-oss-20b (High) (OpenAI)","metrics":{"Index":"20.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763533,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Mistral Medium 3.1 (Mistral)","metrics":{"Index":"20.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763121,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.5 4B (Non-reasoning) (Alibaba)","metrics":{"Index":"20.3"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763211,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-4.1 mini (OpenAI)","metrics":{"Index":"20.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763494,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Mistral Large 3 (Mistral)","metrics":{"Index":"20.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765081,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 1.5 Pro (May '24) (Google)","metrics":{"Index":"19.8"},"paper_url":null,"paper_title":null,"paper_date":"2024-05-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763417,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"DiffusionGemma 26B A4B (Google)","metrics":{"Index":"19.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-06-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763799,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude 3 Opus (Anthropic)","metrics":{"Index":"19.5"},"paper_url":null,"paper_title":null,"paper_date":"2024-03-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765345,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemini 1.0 Ultra (Google)","metrics":{"Index":"17.6"},"paper_url":null,"paper_title":null,"paper_date":"2023-12-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763572,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Granite 4.2 3B (IBM)","metrics":{"Index":"17.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-25","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762980,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3 Next 80B A3B (Reasoning) (Alibaba)","metrics":{"Index":"17.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763081,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"o3-mini (High) (OpenAI)","metrics":{"Index":"16.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-01-31","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763228,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Llama 4 Maverick (Meta)","metrics":{"Index":"16.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764202,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Solar Pro 3 (Upstage)","metrics":{"Index":"16.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763696,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude 3.5 Haiku (Anthropic)","metrics":{"Index":"15.9"},"paper_url":null,"paper_title":null,"paper_date":"2024-10-22","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":761832,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-5 mini (High) (OpenAI)","metrics":{"Index":"15.6"},"paper_url":null,"paper_title":null,"paper_date":"2025-08-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763863,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3 32B (Reasoning) (Alibaba)","metrics":{"Index":"15.3"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763846,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Magistral Small 1.2 (Mistral)","metrics":{"Index":"14.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-09-17","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":762678,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"MiniCPM5-2B (OpenBMB)","metrics":{"Index":"14.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-07","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763732,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) (NVIDIA)","metrics":{"Index":"14.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-15","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765114,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Celeris-1 (Celeris)","metrics":{"Index":"14.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-24","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765217,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Ministral 3 14B (Mistral)","metrics":{"Index":"14.4"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765488,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude 2.1 (Anthropic)","metrics":{"Index":"14"},"paper_url":null,"paper_title":null,"paper_date":"2023-11-21","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763181,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Nemotron 3 Nano Omni 30B A3B Reasoning (NVIDIA)","metrics":{"Index":"13.8"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764045,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3 14B (Reasoning) (Alibaba)","metrics":{"Index":"13.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764902,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-4 (OpenAI)","metrics":{"Index":"13.1"},"paper_url":null,"paper_title":null,"paper_date":"2023-03-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765546,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude 2.0 (Anthropic)","metrics":{"Index":"12.9"},"paper_url":null,"paper_title":null,"paper_date":"2023-07-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763986,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Mistral Small 3.2 (Mistral)","metrics":{"Index":"12.5"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-20","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763341,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3 30B A3B 2507 (Reasoning) (Alibaba)","metrics":{"Index":"12.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-07-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764286,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Llama 3.3 Instruct 70B (Meta)","metrics":{"Index":"11.9"},"paper_url":null,"paper_title":null,"paper_date":"2024-12-06","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764964,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-4o mini (OpenAI)","metrics":{"Index":"11.4"},"paper_url":null,"paper_title":null,"paper_date":"2024-07-18","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764189,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-4.1 nano (OpenAI)","metrics":{"Index":"11.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765566,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"GPT-3.5 Turbo (OpenAI)","metrics":{"Index":"10.7"},"paper_url":null,"paper_title":null,"paper_date":"2022-11-30","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764453,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Granite 4.1 30B (IBM)","metrics":{"Index":"10.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765936,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemma 3 27B Instruct (Google)","metrics":{"Index":"10.1"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763099,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"G9v3-3B (AI9Stars)","metrics":{"Index":"9.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-07-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765581,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Ministral 3 8B (Mistral)","metrics":{"Index":"9.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763917,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Nanbeige4.1-3B (Nanbeige)","metrics":{"Index":"9.6"},"paper_url":null,"paper_title":null,"paper_date":"2026-02-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765022,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Granite 4.1 8B (IBM)","metrics":{"Index":"9.5"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764582,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3 8B (Reasoning) (Alibaba)","metrics":{"Index":"9"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-28","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764086,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Llama 4 Scout (Meta)","metrics":{"Index":"8.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-04-05","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766118,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"NVIDIA Nemotron 3 Nano 4B (NVIDIA)","metrics":{"Index":"8"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-16","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765849,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Claude Instant (Anthropic)","metrics":{"Index":"7.8"},"paper_url":null,"paper_title":null,"paper_date":"2023-03-14","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":763925,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"LFM2.5-2.6B (Liquid AI)","metrics":{"Index":"7.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-08-04","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764224,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemma 4 E2B (Reasoning) (Google)","metrics":{"Index":"7.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766133,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemma 3 12B Instruct (Google)","metrics":{"Index":"5.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764814,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Llama 3.1 Instruct 8B (Meta)","metrics":{"Index":"5.4"},"paper_url":null,"paper_title":null,"paper_date":"2024-07-23","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765951,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Ministral 3 3B (Mistral)","metrics":{"Index":"4.8"},"paper_url":null,"paper_title":null,"paper_date":"2025-12-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765336,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Granite 4.1 3B (IBM)","metrics":{"Index":"4.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-04-29","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765628,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"PALM-2 (Google)","metrics":{"Index":"4.6"},"paper_url":null,"paper_title":null,"paper_date":"2023-05-10","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765136,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Phi-4 Mini Instruct (Microsoft)","metrics":{"Index":"3.8"},"paper_url":null,"paper_title":null,"paper_date":"2024-02-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766142,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"K2 Horizon 0.9B (Institute of Foundation Models)","metrics":{"Index":"3.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-09-03","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":766014,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemma 3n E4B Instruct (Google)","metrics":{"Index":"3.2"},"paper_url":null,"paper_title":null,"paper_date":"2025-06-26","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":764789,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.5 2B (Reasoning) (Alibaba)","metrics":{"Index":"2.9"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765987,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Gemma 3 4B Instruct (Google)","metrics":{"Index":"2.7"},"paper_url":null,"paper_title":null,"paper_date":"2025-03-12","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765157,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.5 2B (Non-reasoning) (Alibaba)","metrics":{"Index":"2.4"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765626,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"Qwen3.5 0.8B (Non-reasoning) (Alibaba)","metrics":{"Index":"1.2"},"paper_url":null,"paper_title":null,"paper_date":"2026-03-02","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]},{"id":765432,"task":"Language Modelling","parent_task":null,"dataset":"Artificial Analysis Coding Index","model_name":"MiniCPM-V 4.6 1.3B (OpenBMB)","metrics":{"Index":"0.7"},"paper_url":null,"paper_title":null,"paper_date":"2026-05-11","code_links":[{"title":"artificialanalysis.ai","url":"https://artificialanalysis.ai/"}],"metrics_order":"[\"Index\"]","area":"Natural Language Processing","uses_additional_data":null,"source":"external","tags":[]}]}