2 vs 0 benchmarks won
Anthropic Claude Opus 4.6 | Moonshot AI Kimi K2 Thinking | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Moonshot AI |
| Release date | Feb 5 2026 | Nov 6 2025 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | 1T |
Context window | — | 256k |
| Benchmarks | ||
Science reasoning GPQA Diamond | 91.3% | — |
Software engineering SWE-Bench Verified | 80.8% | 71.3% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Kimi K2 Thinking shipped 91 days before Claude Opus 4.6 | |
Claude Opus 4.6 leads Kimi K2 Thinking on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Kimi K2 Thinking shipped 91 days before Claude Opus 4.6, so benchmark comparisons should account for the intervening progress.
Kimi K2 Thinking is an open-source / open-weight model; Claude Opus 4.6 is proprietary.
On SWE-Bench Verified, Claude Opus 4.6 scores 80.8%, 9.5 points above Kimi K2 Thinking at 71.3%.