Claude Haiku 4.5 vs GPT-5.4 Pro
As of Oct 14, 2026, Claude Haiku 4.5 leads GPT-5.4 Pro in 0 of 2 shared categories.
Claude Haiku 4.5
#78 Best recorded rank: #78 in Abstraction (ARC), as of Oct 14, 2026.
GPT-5.4 Pro
It used to be. Was SOTA in Math.
| Category | Claude Haiku 4.5 | GPT-5.4 Pro |
|---|---|---|
| General LLM | #104 · #104 in General LLM Margin 70.74829931972789 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Reasoning | #91 · #91 in Reasoning Margin 63.013698630136986 LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Math | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #6 · Was SOTA · Math Margin 11.111111111111114 Epoch AI benchmarking hub · Mar 5, 2026 |
| Science | #109 · #109 in Science Margin — Epoch AI benchmarking hub · Oct 15, 2025 | #6 · #6 in Science Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Coding | #— · Not enough data Margin — Scale Labs leaderboards · Oct 14, 2026 | — |
| Coding › Web dev | #92 · #92 in Coding › Web dev Margin 85.04672897196262 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Long context | #84 · #84 in Long context Margin 57.142857142857146 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Factuality | #97 · #97 in Factuality Margin 73.13432835820896 LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Abstraction (ARC) | #78 · #78 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Oct 15, 2025 | #8 · #8 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
Claude Haiku 4.5: $2.0000000000000004 per 1M blended tokens.
GPT-5.4 Pro: $67.5 per 1M blended tokens.
Claude Haiku 4.5: closed weights.
GPT-5.4 Pro: closed weights.
Science: As of Oct 14, 2026, GPT-5.4 Pro leads Claude Haiku 4.5 in Science at #6 against #109.
Abstraction (ARC): As of Oct 14, 2026, GPT-5.4 Pro leads Claude Haiku 4.5 in Abstraction (ARC) at #8 against #78.
Claude Haiku 4.5 · GPT-5.4 Pro
Claude Haiku 4.5 or GPT-5.4 Pro?
As of Oct 14, 2026, Claude Haiku 4.5 leads GPT-5.4 Pro in 0 of 2 shared categories.
Claude Haiku 4.5 or GPT-5.4 Pro for Science?
As of Oct 14, 2026, GPT-5.4 Pro leads Claude Haiku 4.5 in Science at #6 against #109.
Claude Haiku 4.5 or GPT-5.4 Pro for Abstraction (ARC)?
As of Oct 14, 2026, GPT-5.4 Pro leads Claude Haiku 4.5 in Abstraction (ARC) at #8 against #78.