1 vs 0 benchmarks won
Moonshot AI Kimi K2 Thinking | OpenAI GPT-5.1-Codex-Max | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Nov 6 2025 | Nov 19 2025 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | 1T | — |
Context window | 256k | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | — | — |
Software engineering SWE-Bench Verified | 71.3% | — |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Kimi K2 Thinking shipped 13 days before GPT-5.1-Codex-Max | |
Kimi K2 Thinking leads GPT-5.1-Codex-Max on 1 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Kimi K2 Thinking shipped 13 days before GPT-5.1-Codex-Max, so benchmark comparisons should account for the intervening progress.
Kimi K2 Thinking is an open-source / open-weight model; GPT-5.1-Codex-Max is proprietary.
Direct benchmark comparisons are unavailable — at least one of these models has not published scores on GPQA Diamond, SWE-Bench Verified, or MMMU.