0 vs 2 benchmarks won
Anthropic Claude 3 Opus | Anthropic Claude Opus 4 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Anthropic |
| Release date | Mar 4 2024 | May 22 2025 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 50.4% | 79.6% |
Software engineering SWE-Bench Verified | 33% | 72.5% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Claude 3 Opus shipped 444 days before Claude Opus 4 | |
Claude Opus 4 leads Claude 3 Opus on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude 3 Opus shipped 444 days before Claude Opus 4, 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 scores 79.6%, 29.2 points above Claude 3 Opus at 50.4%. On SWE-Bench Verified, Claude Opus 4 scores 72.5%, 39.5 points above Claude 3 Opus at 33%.