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

Code Generation on HumanEval (Accuracy, Avg.)

81.71Accuracy

Qwen3 8B

33.516446.028258.5471.0518May 25, 2026Jun 1, 2026Jun 8, 2026Jun 15, 2026Jun 22, 2026Jun 29, 2026Jul 7, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2026.07
81.71-
2026.07
81.71-
2026.07
80.49-
2026.07
79.27-
2026.07
79.27-
2026.07
78.7-
2026.07
78.66-
2026.07
77.44-
2026.07
71.04-
2026.07
55.5-
2026.07
49.4-
2026.05
42.0747.29
2026.05
41.4647.09
2026.05
41.4647.89
2026.05
39.0246.34
2026.05
38.4146.76
2026.05
35.3744.66