0 vs 2 benchmarks won
Anthropic Claude Haiku 4.5 | Anthropic Claude Opus 4.6 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Anthropic |
| Release date | Oct 15 2025 | Feb 5 2026 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 73% | 91.3% |
Software engineering SWE-Bench Verified | 73.3% | 80.8% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Claude Haiku 4.5 shipped 113 days before Claude Opus 4.6 | |
Claude Opus 4.6 leads Claude Haiku 4.5 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude Haiku 4.5 shipped 113 days before Claude Opus 4.6, 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 4.6 scores 91.3%, 18.3 points above Claude Haiku 4.5 at 73%. On SWE-Bench Verified, Claude Opus 4.6 scores 80.8%, 7.5 points above Claude Haiku 4.5 at 73.3%.