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

Code Generation on HumanEval (Accuracy, Rank)

20Accuracy

Top-k Sampling

17.9218.461919.54May 10, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
202.63
2026.05
204.75
2026.05
192.33
2026.05
192
2026.05
192.5
2026.05
191.37
2026.05
184.25
2026.05
184.25
2026.05
184.25
2026.05
184.25
2026.05
184.5
2026.05
183.62