0 vs 2 benchmarks won
Meta LLaMA 3.1 | Moonshot AI Kimi K2.5 | |
|---|---|---|
| Overview | ||
| Company | Meta | Moonshot AI |
| Release date | Jul 23 2024 | Jan 27 2026 |
| Model type | — | — |
| Open source | Yes | Yes |
| 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 | LLaMA 3.1 shipped 553 days before Kimi K2.5 | |
Kimi K2.5 leads LLaMA 3.1 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). LLaMA 3.1 shipped 553 days before Kimi K2.5, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
Direct benchmark comparisons are unavailable — at least one of these models has not published scores on GPQA Diamond, SWE-Bench Verified, or MMMU.