0 vs 3 benchmarks won
Moonshot AI Kimi K2 Thinking | OpenAI GPT-5.1 | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Nov 6 2025 | Nov 12 2025 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | 1T | — |
Context window | 256k | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | — | 88.1% |
Software engineering SWE-Bench Verified | 71.3% | 76.3% |
Multimodal understanding MMMU | — | 76% |
| Timeline | ||
| Release gap | Kimi K2 Thinking shipped 6 days before GPT-5.1 | |
GPT-5.1 leads Kimi K2 Thinking on 3 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Kimi K2 Thinking shipped 6 days before GPT-5.1, so benchmark comparisons should account for the intervening progress.
Kimi K2 Thinking is an open-source / open-weight model; GPT-5.1 is proprietary.
On SWE-Bench Verified, GPT-5.1 scores 76.3%, 5 points above Kimi K2 Thinking at 71.3%.