2 vs 0 benchmarks won
Anthropic Claude Opus 4.6 | Moonshot AI Kimi K2.5 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Moonshot AI |
| Release date | Feb 5 2026 | Jan 27 2026 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | 1T |
Context window | — | 256k |
| Benchmarks | ||
Science reasoning GPQA Diamond | 91.3% | 87.6% |
Software engineering SWE-Bench Verified | 80.8% | 76.8% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Kimi K2.5 shipped 9 days before Claude Opus 4.6 | |
Claude Opus 4.6 leads Kimi K2.5 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Kimi K2.5 shipped 9 days before Claude Opus 4.6, so benchmark comparisons should account for the intervening progress.
Kimi K2.5 is an open-source / open-weight model; Claude Opus 4.6 is proprietary.
On GPQA Diamond, Claude Opus 4.6 scores 91.3%, 3.7 points above Kimi K2.5 at 87.6%. On SWE-Bench Verified, Claude Opus 4.6 scores 80.8%, 4 points above Kimi K2.5 at 76.8%.