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.
Overall rank: #19 of 73 open modelscomposite 57.1/100 across 10 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Terminal-Bench | 43.2% | #3 / 16 | #30 / 57 |
| SWE-bench Multilingual | 67.3% | #3 / 4 | #7 / 14 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Humanity's Last Exam | 24.4% | #1 / 4 | #13 / 46 |
| SimpleQA | 33.9% | #6 / 11 | #44 / 65 |
| MMLU-Pro | 87.1% | #3 / 119 | #17 / 259 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 92.2% | #5 / 34 | #28 / 155 |
| FrontierMath | 27.9% | #3 / 12 | #27 / 101 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 87.6% | #5 / 46 | #33 / 182 |
| ARC-AGI | 65.3% | #1 / 10 | #55 / 158 |
| SimpleBench | 46.8% | #7 / 19 | #47 / 90 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.