Skip to content

Benchmark

E-Bench-Code

Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.

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

Score distribution

79%
Mean
79%
Median
0%
Std dev
79%
10th percentile
79%
90th percentile
79%
Min

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.79%

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.