Kimi K2.7 Code — Benchmarks
Benchmark scores for Kimi K2.7 Code aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #32 of 78 open modelscomposite 51.4/100 across 13 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| LiveBench Coding | 74.0 | #11 / 19 | #48 / 63 |
| SciCode | 47.4% | #13 / 62 | #79 / 161 |
| WeirdML | 54.1% | #8 / 46 | #60 / 161 |
| LMArena WebDev | 1472.3 | #16 / 48 | #52 / 123 |
| FrontierCode | 30.1% | #4 / 11 | #22 / 36 |
| DeepSWE | 30.5% | #5 / 5 | #61 / 68 |
| Surface Evolver Bench | 48.8% | #5 / 13 | #18 / 27 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SimpleQA | 36.5% | #7 / 15 | #43 / 80 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| FrontierMath | 54.0% | #8 / 15 | #39 / 102 |
| FrontierMath Tier 4 | 12.2% | #9 / 11 | #52 / 64 |
| LiveBench Math | 79.6 | #18 / 19 | #58 / 63 |
| AIME 2024/2025 | 95.6% | #5 / 82 | #37 / 270 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Chess Puzzles | 21.0% | #7 / 65 | #78 / 205 |
| GPQA Diamond | 87.9% | #13 / 94 | #57 / 289 |
| SimpleBench | 57.9% | #4 / 25 | #37 / 101 |
| CritPt | 10.0% | #9 / 62 | #69 / 172 |
| LiveBench Reasoning | 82.8 | #9 / 19 | #39 / 63 |
| APEX-Agents | 37.6% | #7 / 10 | #27 / 33 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.