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: #4 of 79 open modelscomposite 71.4/100 across 6 benchmarks in 4 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
LiveBench Coding74.0#6 / 26#29 / 75

Knowledge

BenchmarkScoreOpen rankAll models
SimpleQA39.2%#2 / 8#28 / 57

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202596.4%#1 / 31#7 / 147
LiveBench Math79.6#12 / 26#39 / 75

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond89.5%#2 / 43#17 / 174
LiveBench Reasoning82.8#1 / 26#12 / 75

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