0 vs 1 benchmarks won
Google Gemini 2.5 Pro | Moonshot AI Kimi K2 Thinking | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | |
| Release date | Mar 25 2025 | Nov 6 2025 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | 1T |
Context window | — | 256k |
| Benchmarks | ||
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 59.6% | 71.3%Best |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 86.4% | — |
Multimodal MMMUTests the AI on understanding images and text together across many college subjects. Higher is better. | 68% | — |
| Timeline | ||
| Release gap | Gemini 2.5 Pro shipped 226 days before Kimi K2 Thinking | |
Kimi K2 Thinking leads Gemini 2.5 Pro on 1 of the 1 benchmark they both report (SWE-Bench Verified). Gemini 2.5 Pro shipped 226 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.
Kimi K2 Thinking is an open-source / open-weight model; Gemini 2.5 Pro is proprietary.
On SWE-Bench Verified, Kimi K2 Thinking leads at 71.3% vs Gemini 2.5 Pro at 59.6%.