2 vs 1 benchmarks won
Google Gemini 3.0 Pro | Moonshot AI Kimi K2.5 | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | |
| Release date | Nov 18 2025 | Jan 27 2026 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | 1T |
Context window | — | 256k |
| Benchmarks | ||
Science reasoning GPQA Diamond | 91.9% | 87.6% |
Software engineering SWE-Bench Verified | 76.2% | 76.8% |
Multimodal understanding MMMU | 81% | — |
| Timeline | ||
| Release gap | Gemini 3.0 Pro shipped 70 days before Kimi K2.5 | |
Gemini 3.0 Pro leads Kimi K2.5 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Gemini 3.0 Pro shipped 70 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 Pro is proprietary.
On GPQA Diamond, Gemini 3.0 Pro scores 91.9%, 4.3 points above Kimi K2.5 at 87.6%. On SWE-Bench Verified, Kimi K2.5 scores 76.8%, 0.6 points above Gemini 3.0 Pro at 76.2%.