0 vs 2 benchmarks won
DeepSeek DeepSeek Chat (R1-based) | Moonshot AI Kimi K2 (0905) | |
|---|---|---|
| Overview | ||
| Company | DeepSeek | Moonshot AI |
| Release date | Jan 20 2025 | Sep 5 2025 |
| Model type | — | — |
| Open source | Yes | Yes |
| Specifications | ||
Parameters | — | 1T |
Context window | — | 256k |
| Benchmarks | ||
Science reasoning GPQA Diamond | — | 75.1% |
Software engineering SWE-Bench Verified | — | 65.8% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | DeepSeek Chat (R1-based) shipped 228 days before Kimi K2 (0905) | |
Kimi K2 (0905) leads DeepSeek Chat (R1-based) on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). DeepSeek Chat (R1-based) shipped 228 days before Kimi K2 (0905), so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
Direct benchmark comparisons are unavailable — at least one of these models has not published scores on GPQA Diamond, SWE-Bench Verified, or MMMU.