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

Math Reasoning on MMLU-Pro

42.48EM Score

W/O (FP16)

8.555217.362626.1734.9774Nov 9, 2025
Updated 15d ago

Evaluation Results

MethodLinks
2025.11
42.4817.21
2025.11
42.486.76
2025.11
41.65.74
2025.11
41.66.76
2025.11
41.0614.19
2025.11
40.635.75
2025.11
39.895.83
2025.11
39.49.02
2025.11
39.115.95
2025.11
38.579.05
2025.11
38.485.83
2025.11
37.995.95
2025.11
37.55.75
2025.11
35.355.95
2025.11
33.355.95
2025.11
33.214.19
2025.11
33.013.2
2025.11
32.139.05
2025.11
31.015.83
2025.11
30.862.77
2025.11
30.762.25
2025.11
29.155.19
2025.11
28.032.25
2025.11
23.835.19
2025.11
23.545.19
2025.11
18.515.19
2025.11
13.571.93
2025.11
9.862.5