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

Code Reasoning on R-Bench-T Code

49.91Accuracy

DFT

1.518814.081926.64539.2081Oct 31, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
49.9149.91
2025.10
48.5448.54
2025.10
47.7147.71
2025.10
45.745.7
2025.10
45.4345.43
2025.10
41.1341.13
2025.10
35.4735.47
2025.10
35.135.1
2025.10
34.9234.92
2025.10
33.8233.82
2025.10
33.4633.46
2025.10
30.2530.25
2025.10
30.1630.16
2025.10
29.3429.34
2025.10
29.3429.34
2025.10
28.3428.34
2025.10
24.8624.86
2025.10
23.1323.13
2025.10
21.7621.76
2025.10
6.226.22
2025.10
5.215.21
2025.10
4.754.75
2025.10
3.473.47
2025.10
3.383.38