{"id":"gpt-5-4-nano","slug":"gpt-5-4-nano","name":"GPT-5.4 Nano","orgId":"openai","family":"gpt-5-4-nano","releaseDate":"2026-03-17","availability":"ga","openWeights":false,"license":"Proprietary","paramsTotal":null,"contextWindow":400000,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":null,"modalities":["text","file","image"],"aliases":["gpt-5.4-nano-high","GPT-5.4 Nano","gpt-5.4-nano-2026-03-17_none","gpt-5.4-nano-2026-03-17_low","gpt-5.4-nano-2026-03-17_high","gpt-5.4-nano-2026-03-17_xhigh","gpt-5.4-nano-2026-03-17_medium","openai/gpt-5.4-nano","OpenAI: GPT-5.4 Nano"],"aliasNote":null,"organization":{"id":"openai","name":"OpenAI","slug":"openai","country":null,"url":null,"color":"#10A37F","mark":"O"},"price":{"modelId":"gpt-5-4-nano","provider":"openai","inputPerM":null,"outputPerM":null,"blendedPerM":0.4625,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"No.","scope":"Best recorded rank is #43 in Abstraction (ARC).","lead":"As of Oct 14, 2026, GPT-5.4 Nano from OpenAI. Best recorded rank is #43 in Abstraction (ARC). Last listed at #43 in Abstraction (ARC) on 2026-03-17. That board does not award a crown.","confidence":"low"},"verdicts":[{"id":"v_overall_general-llm_gpt-5-4-nano_2026-10-14_open_RANKED","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":113,"present_evidence":[],"missing_evidence":[],"margin":77.24137931034483,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Ranked #113 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#113 in General LLM"},{"id":"v_pareto_general-llm_gpt-5-4-nano_2026-10-14_open_RANKED","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":149,"present_evidence":[],"missing_evidence":[],"margin":79.25531914893617,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Not on the General LLM cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#149 in General LLM"},{"id":"v_overall_reasoning_gpt-5-4-nano_2026-10-14_open_RANKED","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":108,"present_evidence":[],"missing_evidence":[],"margin":75,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Ranked #108 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#108 in Reasoning"},{"id":"v_pareto_reasoning_gpt-5-4-nano_2026-10-14_open_RANKED","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"RANKED","rank":143,"present_evidence":[],"missing_evidence":[],"margin":76.59574468085106,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Not on the Reasoning cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#143 in Reasoning"},{"id":"v_overall_math_gpt-5-4-nano_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","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":84}],"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":"high","rationale":"#84 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-5-4-nano_2026-10-14_open_RANKED","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":73,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Last listed at #73 in Science on 2026-03-17. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#73 in Science"},{"id":"v_overall_coding_gpt-5-4-nano_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","category":"coding","category_name":"Coding","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-text-coding","name":"LMArena Text (style-controlled, coding)","rank":98}],"missing_evidence":[{"benchmark":"terminal-bench-4","name":"Terminal-Bench 4.0"},{"benchmark":"swe-bench-pro-hard","name":"SWE-bench Pro V2 HARD"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"#98 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_long-context_gpt-5-4-nano_2026-10-14_open_RANKED","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":118,"present_evidence":[],"missing_evidence":[],"margin":81.37931034482759,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Ranked #118 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#118 in Long context"},{"id":"v_pareto_long-context_gpt-5-4-nano_2026-10-14_open_RANKED","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","category":"long-context","category_name":"Long context","slice":"pareto","state":"RANKED","rank":157,"present_evidence":[],"missing_evidence":[],"margin":83.51063829787233,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Not on the Long context cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#157 in Long context"},{"id":"v_overall_vision_gpt-5-4-nano_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","category":"vision","category_name":"Vision","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-vision","name":"LMArena Vision (style-controlled)","rank":69}],"missing_evidence":[{"benchmark":"gdp-pdf","name":"GDP.pdf"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"#69 on LMArena Vision (style-controlled); missing GDP.pdf","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_factuality_gpt-5-4-nano_2026-10-14_open_RANKED","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":97,"present_evidence":[],"missing_evidence":[],"margin":73.48484848484848,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Ranked #97 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#97 in Factuality"},{"id":"v_pareto_factuality_gpt-5-4-nano_2026-10-14_open_RANKED","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","category":"factuality","category_name":"Factuality","slice":"pareto","state":"RANKED","rank":126,"present_evidence":[],"missing_evidence":[],"margin":73.83720930232558,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Not on the Factuality cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#126 in Factuality"},{"id":"v_overall_arc_gpt-5-4-nano_2026-10-14_open_RANKED","model":"gpt-5-4-nano","model_name":"GPT-5.4 Nano","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"RANKED","rank":43,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Last listed at #43 in Abstraction (ARC) on 2026-03-17. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#43 in Abstraction (ARC)"}]}