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

28.95232.65136.3540.049Feb 23, 2026Mar 6, 2026Mar 17, 2026Mar 28, 2026Apr 8, 2026Apr 19, 2026May 1, 2026
Updated 29d ago

Evaluation Results

MethodLinks
2026.05
43.259.9
2026.05
42.458.7
2026.05
4152.3
2026.05
39.555.1
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
2026.05
30.540.9
2026.02
29.550.18