Skip to content

Benchmark

Hy4 Expert Blind Eval · Average

Higher scores are better.

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

Score distribution

3
Mean
2.9
Median
0.029
Std dev
2.9
10th percentile
3
90th percentile
2.9
Min
2.93
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Hy4 preview163 internal experts · 203 engineering tasks · blind side-by-side evaluation· Reported by Tencent Hy, Tencent· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.3
2Kimi K3163 internal experts · 203 engineering tasks · blind side-by-side evaluation· Reported by Tencent Hy, Tencent· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.2.9
3GLM 5.3163 internal experts · 203 engineering tasks · blind side-by-side evaluation· Reported by Tencent Hy, Tencent· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.2.9

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.