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

Code Reasoning on HumanEval+

97Pass@16

ResRL

88.6890.849395.16Oct 16, 2025Nov 17, 2025Dec 20, 2025Jan 22, 2026Feb 24, 2026Mar 29, 2026May 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
97-
2026.05
96.9-
2025.10
96.3283.9
2026.02
95.7182.29
2026.05
95.7-
2026.05
95.7-
2026.05
95.7-
2026.02
95.0981.05
2026.02
95.0980.75
2026.02
95.0981.29
2026.02
94.4981.48
2025.10
94.4881.02
2025.10
94.4880.25
2026.02
93.2580.9
2026.05
89-