Skip to content

Benchmark

Kimi Code Bench 2.0

Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.

Models measured
3
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

64.9%
Mean
72.9%
Median
9.3%
Std dev
50.9%
10th percentile
73.7%
90th percentile
50.9%
Min
50.9%73.7%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Kimi K3Claude Code · max effort· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.73.7%
2Kimi K3Kimi Code · max effort· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72.9%
3Kimi K2.7 CodeKimi K2.7 Code official table · Kimi Code CLI · thinking + preserve_thinking · temp 1.0 · top_p .95 · 262,144 context· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.62%
4Kimi K2.6Kimi K2.7 Code official comparison table · Kimi K2.6 · Kimi Code CLI · thinking · temp 1.0 · top_p .95 · 262,144 context· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.50.9%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.