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

BenchmarkScoreOpen rankAll models
SWE-bench Verified65.4%#4 / 13#60 / 163
SWE-bench Bash Only43.8%#7 / 9#38 / 48
Terminal-Bench27.8%#10 / 16#45 / 57
Aider Polyglot59.1%#5 / 18#29 / 69

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro81.0%#19 / 119#59 / 259

Reasoning

BenchmarkScoreOpen rankAll models
SimpleBench26.3%#15 / 19#76 / 90

Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.