Skip to content

Benchmark

Kimi Code Bench v2

Coding benchmarks compare models on programming tasks. Scores are percentages.

Models measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

70.7%
Mean
72.9%
Median
6.4%
Std dev
62%
10th percentile
77.1%
90th percentile
62%
Min
62%77.1%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.1%
2Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.9%
3Kimi K2.7 Code· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62%

Data credits: Data by LLM Stats