Kimi K2 Instruct — Benchmarks
Benchmark scores for Kimi K2 Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #29 of 73 open modelscomposite 51.4/100 across 6 benchmarks in 3 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SWE-bench Verified | 65.4% | #4 / 13 | #60 / 163 |
| SWE-bench Bash Only | 43.8% | #7 / 9 | #38 / 48 |
| Terminal-Bench | 27.8% | #10 / 16 | #45 / 57 |
| Aider Polyglot | 59.1% | #5 / 18 | #29 / 69 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MMLU-Pro | 81.0% | #19 / 119 | #59 / 259 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SimpleBench | 26.3% | #15 / 19 | #76 / 90 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.