{"id":"gpt-5-6-luna","slug":"gpt-5-6-luna","name":"GPT-5.6 Luna","orgId":"openai","family":"gpt-5-6-luna","releaseDate":"2026-06-26","availability":"ga","openWeights":false,"license":"Proprietary","paramsTotal":null,"contextWindow":1050000,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":null,"modalities":["text","file","image"],"aliases":["gpt-5.6-luna-xhigh","GPT-5.6 Luna","gpt-5.6-luna-xhigh (codex-harness)","gpt-5.6-luna_none","gpt-5.6-luna_low","gpt-5.6-luna_max","gpt-5.6-luna_xhigh","gpt-5.6-luna_high","gpt-5.6-luna_medium","gpt-5.6-luna_unknown","GPT-5.6 Luna max","openai/gpt-5.6-luna"],"aliasNote":null,"organization":{"id":"openai","name":"OpenAI","slug":"openai","country":null,"url":null,"color":"#10A37F","mark":"O"},"price":{"modelId":"gpt-5-6-luna","provider":"openai","inputPerM":null,"outputPerM":null,"blendedPerM":0.44999999999999996,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"No.","scope":"Best current rank is #14 in Vision.","lead":"As of Oct 14, 2026, GPT-5.6 Luna from OpenAI. Best current rank is #14 in Vision. Ranked #14 in Vision.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":53,"present_evidence":[],"missing_evidence":[],"margin":35.86206896551724,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Ranked #53 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#53 in General LLM"},{"id":"v_pareto_general-llm_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":66,"present_evidence":[],"missing_evidence":[],"margin":35.1063829787234,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Not on the General LLM cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#66 in General LLM"},{"id":"v_overall_reasoning_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":55,"present_evidence":[],"missing_evidence":[],"margin":38.19444444444444,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Ranked #55 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#55 in Reasoning"},{"id":"v_pareto_reasoning_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"RANKED","rank":69,"present_evidence":[],"missing_evidence":[],"margin":37.234042553191486,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Not on the Reasoning cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#69 in Reasoning"},{"id":"v_overall_math_gpt-5-6-luna_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"math","category_name":"Math","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-text-math","name":"LMArena Text (style-controlled, math)","rank":32}],"missing_evidence":[{"benchmark":"hle","name":"Humanity's Last Exam"},{"benchmark":"frontiermath","name":"FrontierMath"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"#32 on LMArena Text (style-controlled, math); missing Humanity's Last Exam and FrontierMath","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_science_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":25,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"max","rationale":"Last listed at #25 in Science on 2026-07-09. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#25 in Science"},{"id":"v_overall_coding_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"coding","category_name":"Coding","slice":"overall","state":"RANKED","rank":16,"present_evidence":[],"missing_evidence":[],"margin":77.27272727272728,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"max","rationale":"Ranked #16 in Coding.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#16 in Coding"},{"id":"v_pareto_coding_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"coding","category_name":"Coding","slice":"pareto","state":"RANKED","rank":16,"present_evidence":[],"missing_evidence":[],"margin":77.27272727272728,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"max","rationale":"Not on the Coding cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#16 in Coding"},{"id":"v_overall_coding-agentic_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"coding-agentic","category_name":"Coding › Agentic","slice":"overall","state":"RANKED","rank":16,"present_evidence":[],"missing_evidence":[],"margin":77.27272727272728,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"max","rationale":"Ranked #16 in Coding › Agentic.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#16 in Coding › Agentic"},{"id":"v_pareto_coding-agentic_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"coding-agentic","category_name":"Coding › Agentic","slice":"pareto","state":"RANKED","rank":16,"present_evidence":[],"missing_evidence":[],"margin":77.27272727272728,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"max","rationale":"Not on the Coding › Agentic cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#16 in Coding › Agentic"},{"id":"v_overall_coding-web-dev_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"overall","state":"RANKED","rank":41,"present_evidence":[],"missing_evidence":[],"margin":38.095238095238095,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Ranked #41 in Coding › Web dev.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#41 in Coding › Web dev"},{"id":"v_pareto_coding-web-dev_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"pareto","state":"RANKED","rank":46,"present_evidence":[],"missing_evidence":[],"margin":36,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Not on the Coding › Web dev cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#46 in Coding › Web dev"},{"id":"v_overall_long-context_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":64,"present_evidence":[],"missing_evidence":[],"margin":44.13793103448276,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Ranked #64 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#64 in Long context"},{"id":"v_pareto_long-context_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"long-context","category_name":"Long context","slice":"pareto","state":"RANKED","rank":80,"present_evidence":[],"missing_evidence":[],"margin":42.5531914893617,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Not on the Long context cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#80 in Long context"},{"id":"v_overall_vision_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"vision","category_name":"Vision","slice":"overall","state":"RANKED","rank":14,"present_evidence":[],"missing_evidence":[],"margin":47.05882352941177,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"medium","rationale":"Ranked #14 in Vision.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#14 in Vision"},{"id":"v_pareto_vision_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"vision","category_name":"Vision","slice":"pareto","state":"RANKED","rank":14,"present_evidence":[],"missing_evidence":[],"margin":47.05882352941177,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"medium","rationale":"Not on the Vision cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#14 in Vision"},{"id":"v_overall_factuality_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":35,"present_evidence":[],"missing_evidence":[],"margin":26.515151515151516,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Ranked #35 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#35 in Factuality"},{"id":"v_pareto_factuality_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"factuality","category_name":"Factuality","slice":"pareto","state":"RANKED","rank":39,"present_evidence":[],"missing_evidence":[],"margin":23.25581395348837,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Not on the Factuality cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#39 in Factuality"},{"id":"v_overall_arc_gpt-5-6-luna_2026-10-14_open_RANKED","model":"gpt-5-6-luna","model_name":"GPT-5.6 Luna","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"RANKED","rank":18,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"max","rationale":"Last listed at #18 in Abstraction (ARC) on 2026-07-09. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#18 in Abstraction (ARC)"}]}