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

Code Reasoning on LiveCodeBench (LCB)

37.82Accuracy (%)

DFT

-1.51288.698618.9129.1214Oct 31, 2025
Updated 28d ago

Evaluation Results

MethodLinks
2025.10
37.8237.82
2025.10
35.5535.55
2025.10
35.4535.45
2025.10
31.9431.94
2025.10
31.9431.94
2025.10
29.3829.38
2025.10
28.6328.63
2025.10
27.327.3
2025.10
27.227.2
2025.10
26.4526.45
2025.10
26.0726.07
2025.10
25.9725.97
2025.10
25.6925.69
2025.10
25.5925.59
2025.10
25.2125.21
2025.10
24.8324.83
2025.10
24.7424.74
2025.10
22.5622.56
2025.10
10.3310.33
2025.10
9.679.67
2025.10
9.299.29
2025.10
99
2025.10
6.166.16
2025.10
00