GPT-5.4 vs GPT-5 Mini
As of Oct 14, 2026, GPT-5.4 leads GPT-5 Mini in 7 of 7 shared categories: General LLM, Reasoning, Math, Science, Long context, Factuality, and Abstraction (ARC).
| Category | GPT-5.4 | GPT-5 Mini |
|---|---|---|
| General LLM | #28 · Was SOTA · General LLM Margin 19.04761904761905 LMArena leaderboard dataset · Oct 13, 2026 | #128 · #128 in General LLM Margin 87.07482993197279 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #29 · #29 in Reasoning Margin 20.54794520547945 LMArena leaderboard dataset · Oct 13, 2026 | #130 · #130 in Reasoning Margin 89.72602739726028 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #9 · #9 in Math Margin 17.777777777777757 Epoch AI benchmarking hub · Mar 5, 2026 | #21 · Was SOTA · Math Margin 44.44444444444444 Epoch AI benchmarking hub · Aug 7, 2025 |
| Science | #16 · #16 in Science Margin — Epoch AI benchmarking hub · Mar 5, 2026 | #81 · #81 in Science Margin — Epoch AI benchmarking hub · Aug 7, 2025 |
| Coding | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Aug 7, 2025 |
| Coding › Web dev | #55 · #55 in Coding › Web dev Margin 50.467289719626166 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Long context | #34 · #34 in Long context Margin 23.12925170068027 LMArena leaderboard dataset · Oct 13, 2026 | #146 · #146 in Long context Margin 99.31972789115646 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 |
| Factuality | #6 · Was SOTA · Factuality Margin 5.22388059701494 LMArena leaderboard dataset · Oct 13, 2026 | #110 · #110 in Factuality Margin 82.83582089552239 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #10 · #10 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Mar 5, 2026 | #41 · #41 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Aug 7, 2025 |
GPT-5.4: $5.625 per 1M blended tokens.
GPT-5 Mini: $0.6875 per 1M blended tokens.
GPT-5.4: closed weights.
GPT-5 Mini: closed weights.
General LLM: As of Oct 14, 2026, GPT-5.4 leads GPT-5 Mini in General LLM at #28 against #128.
Reasoning: As of Oct 14, 2026, GPT-5.4 leads GPT-5 Mini in Reasoning at #29 against #130.
Math: As of Oct 14, 2026, GPT-5.4 leads GPT-5 Mini in Math at #9 against #21.
Science: As of Oct 14, 2026, GPT-5.4 leads GPT-5 Mini in Science at #16 against #81.
Long context: As of Oct 14, 2026, GPT-5.4 leads GPT-5 Mini in Long context at #34 against #146.
Factuality: As of Oct 14, 2026, GPT-5.4 leads GPT-5 Mini in Factuality at #6 against #110.
Abstraction (ARC): As of Oct 14, 2026, GPT-5.4 leads GPT-5 Mini in Abstraction (ARC) at #10 against #41.
GPT-5.4 or GPT-5 Mini?
As of Oct 14, 2026, GPT-5.4 leads GPT-5 Mini in 7 of 7 shared categories: General LLM, Reasoning, Math, Science, Long context, Factuality, and Abstraction (ARC).
GPT-5.4 or GPT-5 Mini for General LLM?
As of Oct 14, 2026, GPT-5.4 leads GPT-5 Mini in General LLM at #28 against #128.
GPT-5.4 or GPT-5 Mini for Reasoning?
As of Oct 14, 2026, GPT-5.4 leads GPT-5 Mini in Reasoning at #29 against #130.
GPT-5.4 or GPT-5 Mini for Math?
As of Oct 14, 2026, GPT-5.4 leads GPT-5 Mini in Math at #9 against #21.