Skip to content

Benchmark

Hy4 vs GLM-5.3 · Loss

Scores are percentages. Lower is better.

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

Score distribution

40.4%
Mean
40.4%
Median
0%
Std dev
40.4%
10th percentile
40.4%
90th percentile
40.4%
Min

Results

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

ModelScore
Hy4 preview163 internal experts · 203 engineering tasks · blind side-by-side evaluation· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.40.4%

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.