1 vs 2 benchmarks won
Google Gemini 2.5 Pro | Moonshot AI Kimi K2.5 | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | |
| Release date | Mar 25 2025 | Jan 27 2026 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | 1T |
Context window | — | 256k |
| Benchmarks | ||
Science reasoning GPQA Diamond | 86.4% | 87.6% |
Software engineering SWE-Bench Verified | 59.6% | 76.8% |
Multimodal understanding MMMU | 68% | — |
| Timeline | ||
| Release gap | Gemini 2.5 Pro shipped 308 days before Kimi K2.5 | |
Kimi K2.5 leads Gemini 2.5 Pro on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Gemini 2.5 Pro shipped 308 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 2.5 Pro is proprietary.
On GPQA Diamond, Kimi K2.5 scores 87.6%, 1.2 points above Gemini 2.5 Pro at 86.4%. On SWE-Bench Verified, Kimi K2.5 scores 76.8%, 17.2 points above Gemini 2.5 Pro at 59.6%.