2 vs 0 benchmarks won
Google Gemini 3.0 Flash | Moonshot AI Kimi K2.5 | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | |
| Release date | Dec 17 2025 | Jan 27 2026 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | 1T |
Context window | — | 256k |
| Benchmarks | ||
Science reasoning GPQA Diamond | 90.4% | 87.6% |
Software engineering SWE-Bench Verified | 78% | 76.8% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Gemini 3.0 Flash shipped 41 days before Kimi K2.5 | |
Gemini 3.0 Flash leads Kimi K2.5 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Gemini 3.0 Flash shipped 41 days before Kimi K2.5, so benchmark comparisons should account for the intervening progress.
Kimi K2.5 is an open-source / open-weight model; Gemini 3.0 Flash is proprietary.
On GPQA Diamond, Gemini 3.0 Flash scores 90.4%, 2.8 points above Kimi K2.5 at 87.6%. On SWE-Bench Verified, Gemini 3.0 Flash scores 78%, 1.2 points above Kimi K2.5 at 76.8%.