Skip to content

Benchmark

HLE-Verified¹

Scores are percentages. Higher is better.

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

Score distribution

48.7%
Mean
53.6%
Median
7.9%
Std dev
37.6%
10th percentile
54.9%
90th percentile
37.6%
Min
37.6%54.9%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Gemini 3.8 Flashfull verified set · 1,811 items· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.9%
2Gemini 3.7 Flash1,811 verified items· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.53.6%
3Qwen3.5 397B A17BQwen3.5 release/model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.37.6%

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.