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

Code Generation on MultiPL-E MBPP

58.8Score

Kimi-K2

50.27252.48654.756.914Jan 6, 2026Jan 12, 2026Jan 18, 2026Jan 24, 2026Jan 30, 2026Feb 5, 2026Feb 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
58.8-
2026.01
58.8-
2026.02
58-
2026.02
56.7-
2026.01
56.7-
2026.02
52.5-
2026.01
52.5-
2026.02
50.6-
2026.01
50.6-
2026.06
-82.1
2026.06
-81.6
2026.06
-81.1