0 vs 2 benchmarks won
Google Gemini 2.5 Flash Image | Moonshot AI Kimi K2 | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | |
| Release date | Aug 26 2025 | Jul 11 2025 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | 1T |
Context window | — | 128k |
| Benchmarks | ||
Science reasoning GPQA Diamond | — | 75.1% |
Software engineering SWE-Bench Verified | — | 65.8% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Kimi K2 shipped 46 days before Gemini 2.5 Flash Image | |
Kimi K2 leads Gemini 2.5 Flash Image on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Kimi K2 shipped 46 days before Gemini 2.5 Flash Image, so benchmark comparisons should account for the intervening progress.
Kimi K2 is an open-source / open-weight model; Gemini 2.5 Flash Image 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.