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

Code Generation on HumanEval (Accuracy (%), Avg.)

58.54Accuracy (%)

FP

4.636818.630932.62546.6191Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
58.5470.01
2026.06
57.9371.01
2026.06
44.5166.66
2026.06
41.4664.64
2026.06
41.4663.98
2026.06
38.4162.08
2026.06
32.3261.14
2026.06
23.1757.49
2026.06
13.0545.76
2026.06
6.7142