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: #6 of 73 open modelscomposite 69.2/100 across 7 benchmarks in 4 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
LiveBench Coding74.0#3 / 8#27 / 37

Knowledge

BenchmarkScoreOpen rankAll models
SimpleQA39.2%#3 / 11#33 / 65

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202596.4%#2 / 34#12 / 155
LiveBench Math79.6#7 / 8#34 / 37

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond89.5%#3 / 46#24 / 182
LiveBench Reasoning82.8#1 / 8#22 / 37
SimpleBench57.9%#2 / 19#30 / 90

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