GPT-5 vs GPT-5.4 Pro
As of Oct 14, 2026, GPT-5 leads GPT-5.4 Pro in 0 of 3 shared categories.
| Category | GPT-5 | GPT-5.4 Pro |
|---|---|---|
| General LLM | #76 · Was SOTA · General LLM Margin 51.70068027210884 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Reasoning | #78 · Was SOTA · Reasoning Margin 54.10958904109589 LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Math | #15 · Was SOTA · Math Margin 31.111111111111114 Epoch AI benchmarking hub · Aug 7, 2025 | #6 · Was SOTA · Math Margin 11.111111111111114 Epoch AI benchmarking hub · Mar 5, 2026 |
| Science | #54 · #54 in Science Margin — Epoch AI benchmarking hub · Aug 7, 2025 | #6 · #6 in Science Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Coding | #— · Not enough data Margin — Epoch AI benchmarking hub · Aug 7, 2025 | — |
| Coding › Web dev | #66 · #66 in Coding › Web dev Margin 60.74766355140187 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Long context | #107 · Was SOTA · Long context Margin 72.78911564625851 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Vision | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 | — |
| Factuality | #93 · #93 in Factuality Margin 70.14925373134328 LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Abstraction (ARC) | #34 · #34 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Aug 7, 2025 | #8 · #8 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
GPT-5: $3.4375000000000004 per 1M blended tokens.
GPT-5.4 Pro: $67.5 per 1M blended tokens.
GPT-5: closed weights.
GPT-5.4 Pro: closed weights.
Math: As of Oct 14, 2026, GPT-5.4 Pro leads GPT-5 in Math at #6 against #15.
Science: As of Oct 14, 2026, GPT-5.4 Pro leads GPT-5 in Science at #6 against #54.
Abstraction (ARC): As of Oct 14, 2026, GPT-5.4 Pro leads GPT-5 in Abstraction (ARC) at #8 against #34.
GPT-5 or GPT-5.4 Pro?
As of Oct 14, 2026, GPT-5 leads GPT-5.4 Pro in 0 of 3 shared categories.
GPT-5 or GPT-5.4 Pro for Math?
As of Oct 14, 2026, GPT-5.4 Pro leads GPT-5 in Math at #6 against #15.
GPT-5 or GPT-5.4 Pro for Science?
As of Oct 14, 2026, GPT-5.4 Pro leads GPT-5 in Science at #6 against #54.
GPT-5 or GPT-5.4 Pro for Abstraction (ARC)?
As of Oct 14, 2026, GPT-5.4 Pro leads GPT-5 in Abstraction (ARC) at #8 against #34.