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

Code Generation on HumanEval (Score and Step metrics)

43.29Score

AHD

36.32238.13139.9441.749Apr 10, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.04
43.2977.24
2026.04
41.4678.36
2026.04
40.85256
2026.04
40.85131.48
2026.04
40.24256
2026.04
36.5982.83