2 vs 1 benchmarks won
Anthropic Claude Sonnet 4.5 | OpenAI GPT-5.4-Pro | |
|---|---|---|
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Sep 29 2025 | Mar 5 2026 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 83.4% | 94.4% |
Software engineering SWE-Bench Verified | 77.2% | — |
Multimodal understanding MMMU | 68% | — |
| Timeline | ||
| Release gap | Claude Sonnet 4.5 shipped 157 days before GPT-5.4-Pro | |
Claude Sonnet 4.5 leads GPT-5.4-Pro on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude Sonnet 4.5 shipped 157 days before GPT-5.4-Pro, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On GPQA Diamond, GPT-5.4-Pro scores 94.4%, 11 points above Claude Sonnet 4.5 at 83.4%.