Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Code Generation on HumanEval (Average Acceptance Length (τ), Speedup Ratio)

7.23Avg Acceptance Length (τ)

PPOW

5.4625.9216.386.839May 14, 2026
Updated 19d ago

Evaluation Results

MethodLinks
2026.05
7.234.14
2026.05
7.013.62
2026.05
6.964.82
2026.05
6.914.16
2026.05
6.784.8
2026.05
6.723.96
2026.05
6.694.78
2026.05
6.683.4
2026.05
6.633.92
2026.05
6.574.62
2026.05
6.524.02
2026.05
6.333.37
2026.05
6.314.46
2026.05
6.284.43
2026.05
6.172.77
2026.05
6.013.29
2026.05
5.962.33
2026.05
5.943.25
2026.05
5.712.11
2026.05
5.532.59