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

Math Reasoning on R-Bench-T Math

54.48Accuracy

DFT

0.76414.709528.65542.6005Oct 31, 2025
Updated 28d ago

Evaluation Results

MethodLinks
2025.10
54.4854.48
2025.10
49.9149.91
2025.10
46.1646.16
2025.10
45.845.8
2025.10
43.3343.33
2025.10
41.1341.13
2025.10
38.6738.67
2025.10
35.4735.47
2025.10
35.4735.47
2025.10
35.3735.37
2025.10
35.0135.01
2025.10
34.6434.64
2025.10
3434
2025.10
31.3531.35
2025.10
30.7130.71
2025.10
28.7928.79
2025.10
24.8624.86
2025.10
23.1323.13
2025.10
21.7621.76
2025.10
7.957.95
2025.10
6.226.22
2025.10
4.024.02
2025.10
3.563.56
2025.10
2.832.83