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

Mathematical Reasoning on MathVerse V

67.8Accuracy

EASE-7B

29.42439.38749.3559.313May 1, 2026May 5, 2026May 10, 2026May 15, 2026May 19, 2026May 24, 2026May 29, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.05
67.8
2026.05
67.6
2026.05
67.6
2026.05
66.6
2026.05
64.8
2026.05
63.6
2026.05
59.8
2026.05
58.9
2026.05
58.5
2026.05
57.9
2026.05
57.6
2026.05
57.5
2026.05
57.4
2026.05
56.9
2026.05
56.1
2026.05
55
2026.05
55
2026.05
55
2026.05
54.6
2026.05
54.4
2026.05
54.2
2026.05
52.9
2026.05
52.9
2026.05
52.7
2026.05
52.4
2026.05
52.4
2026.05
51.7
2026.05
30.9