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

Mathematical Reasoning on SVAMP (FRS, pass@1 accuracy)

94.3Pass@1 Accuracy

MT

7.35629.92852.575.072Apr 14, 2026Apr 17, 2026Apr 21, 2026Apr 24, 2026Apr 28, 2026May 1, 2026May 5, 2026
Updated 27d ago

Evaluation Results

MethodLinks
2026.04
94.3-
2026.04
85.9-
2026.04
85.8-
2026.04
85.5-
2026.04
85-
2026.04
84.7-
2026.04
84.3-
2026.05
79-
2026.05
73.7-
2026.05
45.6-
2026.04
21.7-
2026.05
14.6-
2026.05
13.6-
2026.05
10.7-
2026.04
-99
2026.04
-96.9
2026.04
-91
2026.04
-75.5
2026.04
-74.5
2026.04
-74.8
2026.04
-64.9
2026.04
-80
2026.04
-31.1