0 vs 2 benchmarks won
Anthropic Claude 3.5 Sonnet | Anthropic Claude Opus 4.5 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Anthropic |
| Release date | Jun 20 2024 | Nov 24 2025 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 59.4% | 87% |
Software engineering SWE-Bench Verified | 33.4% | 80.9% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Claude 3.5 Sonnet shipped 522 days before Claude Opus 4.5 | |
Claude Opus 4.5 leads Claude 3.5 Sonnet on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude 3.5 Sonnet shipped 522 days before Claude Opus 4.5, 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, Claude Opus 4.5 scores 87%, 27.6 points above Claude 3.5 Sonnet at 59.4%. On SWE-Bench Verified, Claude Opus 4.5 scores 80.9%, 47.5 points above Claude 3.5 Sonnet at 33.4%.