Claude 3.7 Sonnet 20250219 vs GPT-5.4 Pro
As of Oct 14, 2026, Claude 3.7 Sonnet 20250219 leads GPT-5.4 Pro in 0 of 2 shared categories.
Claude 3.7 Sonnet 20250219
#61 Best recorded rank: #61 in Abstraction (ARC), as of Oct 14, 2026.
GPT-5.4 Pro
It used to be. Was SOTA in Math.
| Category | Claude 3.7 Sonnet 20250219 | GPT-5.4 Pro |
|---|---|---|
| Reasoning | #— · Not enough data Margin — Epoch AI benchmarking hub · Feb 24, 2025 | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Math | — | #6 · Was SOTA · Math Margin 11.111111111111114 Epoch AI benchmarking hub · Mar 5, 2026 |
| Science | #72 · #72 in Science Margin — Epoch AI benchmarking hub · Feb 24, 2025 | #6 · #6 in Science Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Factuality | — | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Abstraction (ARC) | #61 · #61 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Feb 24, 2025 | #8 · #8 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
Claude 3.7 Sonnet 20250219: price per 1M tokens is unset in the catalog.
GPT-5.4 Pro: $67.5 per 1M blended tokens.
Claude 3.7 Sonnet 20250219: closed weights.
GPT-5.4 Pro: closed weights.
Science: As of Oct 14, 2026, GPT-5.4 Pro leads Claude 3.7 Sonnet 20250219 in Science at #6 against #72.
Abstraction (ARC): As of Oct 14, 2026, GPT-5.4 Pro leads Claude 3.7 Sonnet 20250219 in Abstraction (ARC) at #8 against #61.
Claude 3.7 Sonnet 20250219 · GPT-5.4 Pro
Claude 3.7 Sonnet 20250219 or GPT-5.4 Pro?
As of Oct 14, 2026, Claude 3.7 Sonnet 20250219 leads GPT-5.4 Pro in 0 of 2 shared categories.
Claude 3.7 Sonnet 20250219 or GPT-5.4 Pro for Science?
As of Oct 14, 2026, GPT-5.4 Pro leads Claude 3.7 Sonnet 20250219 in Science at #6 against #72.
Claude 3.7 Sonnet 20250219 or GPT-5.4 Pro for Abstraction (ARC)?
As of Oct 14, 2026, GPT-5.4 Pro leads Claude 3.7 Sonnet 20250219 in Abstraction (ARC) at #8 against #61.