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

Code Generation on HumanEval+, MBPP+, and BigCodeBench Aggregate

70.72Average Score

Code-A1

50.429655.697360.96566.2327Mar 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
70.72
2026.03
70.39
2026.03
70.37
2026.03
68.35
2026.03
66.15
2026.03
65.14
2026.03
64.67
2026.03
60.84
2026.03
56.95
2026.03
56.23
2026.03
55.88
2026.03
51.21