Skip to content

Benchmark

E-Bench

Scores are percentages. Higher is better.

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

63.7%
Mean
77.1%
Median
13.4%
Std dev
50.2%
10th percentile
77.1%
90th percentile
50.2%
Min
50.2%77.1%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Hy4 previewinternal· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.1%
2Hy3 (Deep Infra)Hy3 official Benchmark Appendix · highest reasoning tier unless noted · internal· Reported by Tencent Hunyuan· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.50.2%

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.