2 vs 0 benchmarks won
Moonshot AI Kimi K2.5 | OpenAI GPT-4.1 mini | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | OpenAI |
| Release date | Jan 27 2026 | May 14 2025 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | 1T | — |
Context window | 256k | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 87.6% | — |
Software engineering SWE-Bench Verified | 76.8% | — |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | GPT-4.1 mini shipped 258 days before Kimi K2.5 | |
Kimi K2.5 leads GPT-4.1 mini on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). GPT-4.1 mini shipped 258 days before Kimi K2.5, so benchmark comparisons should account for the intervening progress.
Kimi K2.5 is an open-source / open-weight model; GPT-4.1 mini 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.