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

Code Reasoning on LiveCodeBench (Avg@16, Pass@16)

43.2Avg@16

ResRL

28.95232.65136.3540.049Oct 16, 2025Nov 17, 2025Dec 20, 2025Jan 22, 2026Feb 24, 2026Mar 29, 2026May 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
43.259.9
2026.05
42.458.7
2026.05
4152.3
2026.05
39.555.1
2025.10
36.0254.48
2025.10
33.9253.41
2026.02
33.5151.97
2026.02
33.2451.61
2026.05
32.852.3
2026.02
32.7550.9
2026.02
32.4651.25
2026.02
32.151.97
2025.10
30.8547.31
2026.05
30.540.9
2026.02
29.550.18