Kimi K2.5 — Benchmarks
Benchmark scores for Kimi K2.5 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Coding
| Benchmark | Score | Rank |
|---|---|---|
| SWE-bench Verified | 73.8% | #3 / 4 |
| Terminal-Bench | 43.2% | #3 / 15 |
| LiveBench Coding | 77.9 | #2 / 23 |
Knowledge
| Benchmark | Score | Rank |
|---|---|---|
| Humanity's Last Exam | 24.4% | #1 / 4 |
| SimpleQA | 33.9% | #4 / 7 |
Math
| Benchmark | Score | Rank |
|---|---|---|
| AIME 2024/2025 | 92.2% | #3 / 29 |
| FrontierMath | 27.9% | #3 / 12 |
| LiveBench Math | 84.9 | #4 / 23 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| GPQA Diamond | 87.6% | #3 / 41 |
| ARC-AGI | 65.3% | #1 / 10 |
| SimpleBench | 46.8% | #5 / 15 |
| LiveBench Reasoning | 76.0 | #4 / 23 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.