GPT-5.4 Mini vs O3 Mini
As of Oct 14, 2026, GPT-5.4 Mini leads O3 Mini in 4 of 5 shared categories: Reasoning, Science, Long context, and Abstraction (ARC).
GPT-5.4 Mini
#36 Best recorded rank: #36 in Abstraction (ARC), as of Oct 14, 2026.
O3 Mini
It used to be. Was SOTA in Reasoning.
| Category | GPT-5.4 Mini | O3 Mini |
|---|---|---|
| General LLM | #59 · #59 in General LLM Margin 40.136054421768705 LMArena leaderboard dataset · Oct 13, 2026 | #7 · #7 in General LLM Margin — LMArena leaderboard dataset · Apr 16, 2025 |
| Reasoning | #59 · #59 in Reasoning Margin 41.0958904109589 LMArena leaderboard dataset · Oct 13, 2026 | #133 · Was SOTA · Reasoning Margin 91.78082191780823 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Science | #52 · #52 in Science Margin — Epoch AI benchmarking hub · Mar 17, 2026 | #76 · #76 in Science Margin — Epoch AI benchmarking hub · Jan 31, 2025 |
| Coding | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Coding › Web dev | #74 · #74 in Coding › Web dev Margin 68.22429906542055 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Long context | #71 · #71 in Long context Margin 48.29931972789117 LMArena leaderboard dataset · Oct 13, 2026 | #145 · #145 in Long context Margin 98.63945578231292 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 | — |
| Factuality | #54 · #54 in Factuality Margin 41.04477611940298 LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Jan 31, 2025 |
| Abstraction (ARC) | #36 · #36 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Mar 17, 2026 | #51 · #51 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Jan 31, 2025 |
GPT-5.4 Mini: $1.6875 per 1M blended tokens.
O3 Mini: $1.9250000000000003 per 1M blended tokens.
GPT-5.4 Mini: closed weights.
O3 Mini: closed weights.
General LLM: As of Oct 14, 2026, O3 Mini leads GPT-5.4 Mini in General LLM at #7 against #59.
Reasoning: As of Oct 14, 2026, GPT-5.4 Mini leads O3 Mini in Reasoning at #59 against #133.
Science: As of Oct 14, 2026, GPT-5.4 Mini leads O3 Mini in Science at #52 against #76.
Long context: As of Oct 14, 2026, GPT-5.4 Mini leads O3 Mini in Long context at #71 against #145.
Abstraction (ARC): As of Oct 14, 2026, GPT-5.4 Mini leads O3 Mini in Abstraction (ARC) at #36 against #51.
GPT-5.4 Mini or O3 Mini?
As of Oct 14, 2026, GPT-5.4 Mini leads O3 Mini in 4 of 5 shared categories: Reasoning, Science, Long context, and Abstraction (ARC).
GPT-5.4 Mini or O3 Mini for General LLM?
As of Oct 14, 2026, O3 Mini leads GPT-5.4 Mini in General LLM at #7 against #59.
GPT-5.4 Mini or O3 Mini for Reasoning?
As of Oct 14, 2026, GPT-5.4 Mini leads O3 Mini in Reasoning at #59 against #133.
GPT-5.4 Mini or O3 Mini for Science?
As of Oct 14, 2026, GPT-5.4 Mini leads O3 Mini in Science at #52 against #76.