GPT-5.4 Mini vs GPT-5.5
As of Oct 14, 2026, GPT-5.4 Mini leads GPT-5.5 in 0 of 7 shared categories.
GPT-5.4 Mini
#36 Best recorded rank: #36 in Abstraction (ARC), as of Oct 14, 2026.
GPT-5.5
It used to be. Was SOTA in General LLM.
| Category | GPT-5.4 Mini | GPT-5.5 |
|---|---|---|
| General LLM | #59 · #59 in General LLM Margin 40.136054421768705 LMArena leaderboard dataset · Oct 13, 2026 | #21 · Was SOTA · General LLM Margin 14.285714285714292 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #59 · #59 in Reasoning Margin 41.0958904109589 LMArena leaderboard dataset · Oct 13, 2026 | #25 · #25 in Reasoning Margin 17.808219178082197 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 | #30 · #30 in Science Margin — Epoch AI benchmarking hub · Apr 23, 2026 |
| 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 | #44 · #44 in Coding › Web dev Margin 40.18691588785047 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | #71 · #71 in Long context Margin 48.29931972789117 LMArena leaderboard dataset · Oct 13, 2026 | #23 · Was SOTA · Long context Margin 15.646258503401356 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 | #10 · Was SOTA · Vision Margin 28.94736842105263 Epoch AI benchmarking hub · Apr 23, 2026 |
| Factuality | #54 · #54 in Factuality Margin 41.04477611940298 LMArena leaderboard dataset · Oct 13, 2026 | #5 · Was SOTA · Factuality Margin 4.477611940298502 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #36 · #36 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Mar 17, 2026 | #7 · #7 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Apr 23, 2026 |
GPT-5.4 Mini: $1.6875 per 1M blended tokens.
GPT-5.5: $11.25 per 1M blended tokens.
GPT-5.4 Mini: closed weights.
GPT-5.5: closed weights.
General LLM: As of Oct 14, 2026, GPT-5.5 leads GPT-5.4 Mini in General LLM at #21 against #59.
Reasoning: As of Oct 14, 2026, GPT-5.5 leads GPT-5.4 Mini in Reasoning at #25 against #59.
Science: As of Oct 14, 2026, GPT-5.5 leads GPT-5.4 Mini in Science at #30 against #52.
Coding › Web dev: As of Oct 14, 2026, GPT-5.5 leads GPT-5.4 Mini in Coding › Web dev at #44 against #74.
Long context: As of Oct 14, 2026, GPT-5.5 leads GPT-5.4 Mini in Long context at #23 against #71.
Factuality: As of Oct 14, 2026, GPT-5.5 leads GPT-5.4 Mini in Factuality at #5 against #54.
Abstraction (ARC): As of Oct 14, 2026, GPT-5.5 leads GPT-5.4 Mini in Abstraction (ARC) at #7 against #36.
GPT-5.4 Mini or GPT-5.5?
As of Oct 14, 2026, GPT-5.4 Mini leads GPT-5.5 in 0 of 7 shared categories.
GPT-5.4 Mini or GPT-5.5 for General LLM?
As of Oct 14, 2026, GPT-5.5 leads GPT-5.4 Mini in General LLM at #21 against #59.
GPT-5.4 Mini or GPT-5.5 for Reasoning?
As of Oct 14, 2026, GPT-5.5 leads GPT-5.4 Mini in Reasoning at #25 against #59.
GPT-5.4 Mini or GPT-5.5 for Science?
As of Oct 14, 2026, GPT-5.5 leads GPT-5.4 Mini in Science at #30 against #52.