1 vs 1 benchmarks won
Moonshot AI Kimi K2 | OpenAI GPT-5.4-Pro | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Jul 11 2025 | Mar 5 2026 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | 1T | — |
Context window | 128k | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 75.1% | 94.4% |
Software engineering SWE-Bench Verified | 65.8% | — |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Kimi K2 shipped 237 days before GPT-5.4-Pro | |
Kimi K2 and GPT-5.4-Pro are evenly matched across the benchmarks they both publish. Kimi K2 shipped 237 days before GPT-5.4-Pro, so benchmark comparisons should account for the intervening progress.
Kimi K2 is an open-source / open-weight model; GPT-5.4-Pro is proprietary.
On GPQA Diamond, GPT-5.4-Pro scores 94.4%, 19.3 points above Kimi K2 at 75.1%.