Skip to content

Benchmark

Claw-Eval · 20260325 · Pass³

Scores are percentages. Higher is better.

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

Score distribution

68.5%
Mean
68.5%
Median
0%
Std dev
68.5%
10th percentile
68.5%
90th percentile
68.5%
Min

Leaderboard

#ModelScore
1Hy3 (Deep Infra)Hy3 official Benchmark Appendix · highest reasoning tier unless noted · internal harness · 105 queries · Gemini 3.5 Flash judge· Reported by Tencent Hunyuan· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.68.5%

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.