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

Math Reasoning on SVAMP (Accuracy, Reasoning Length)

78.67Accuracy

HypLoRA

8.605226.795144.98563.1749Jan 30, 2026Feb 24, 2026Mar 21, 2026Apr 15, 2026May 10, 2026Jun 4, 2026Jun 29, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.02
78.67-
2026.02
78-
2026.02
76.33-
2026.02
75.33-
2026.02
74.67-
2026.06
67.73.8
2026.06
67.363.4
2026.06
66.761.8
2026.06
57.33.5
2026.06
53.732
2026.06
52.30
2026.01
50.12.02
2026.06
50.12
2026.06
49.33.2
2026.01
47.12.96
2026.06
47.13
2026.06
41.56
2026.06
41.30
2026.01
39.86
2026.06
39.86
2026.01
36.40
2026.06
36.40
2026.01
21.76
2026.06
21.76
2026.06
11.36