0 vs 2 benchmarks won
Moonshot AI Kimi K2 Thinking | OpenAI GPT-5.2 | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Nov 6 2025 | Dec 11 2025 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | 1T | — |
Context window | 256k | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | — | 92.4% |
Software engineering SWE-Bench Verified | 71.3% | 80% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Kimi K2 Thinking shipped 35 days before GPT-5.2 | |
GPT-5.2 leads Kimi K2 Thinking on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Kimi K2 Thinking shipped 35 days before GPT-5.2, so benchmark comparisons should account for the intervening progress.
Kimi K2 Thinking is an open-source / open-weight model; GPT-5.2 is proprietary.
On SWE-Bench Verified, GPT-5.2 scores 80%, 8.7 points above Kimi K2 Thinking at 71.3%.