Skip to content

Benchmark

V* · With CI

Scores are percentages. Higher is better.

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

Score distribution

96.2%
Mean
96.9%
Median
0.698%
Std dev
95.3%
10th percentile
96.9%
90th percentile
95.3%
Min
95.3%96.9%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Kimi K2.6Kimi K2.6 official benchmark table · thinking · temp 1.0 · top_p 1.0 · 262,144 context · with Python · max 50 steps · avg@3· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.96.9%
2Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise · with CI· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.96.9%
3Qwen3.5 397B A17BQwen3.5 release/model card · with Code Interpreter· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.95.8%
4Step 3.7 FlashStep 3.7 Flash official README/figure · with Python· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.95.3%

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.