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

Math Reasoning on MathVista (pass@1, avg@8)

79.6Avg Pass@8

ADHint

43.252.6562.171.55Dec 15, 2025Jan 10, 2026Feb 5, 2026Mar 3, 2026Mar 29, 2026Apr 24, 2026May 21, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2025.12
79.674
2025.12
78.874.6
2025.12
74.874.4
2025.12
73.473.4
2025.12
71.164.7
2025.12
68.759
2026.05
66.4-
2026.05
65.3-
2026.05
64.6-
2026.05
64.5-
2025.12
64.464.9
2026.05
64.4-
2025.12
64.364.8
2025.12
64.365.9
2025.12
63.966.1
2026.05
63.9-
2026.05
63.7-
2025.12
63.353.6
2025.12
63.163.9
2025.12
61.351.9
2025.12
61.263.6
2025.12
55.257.3
2025.12
52.556.7
2025.12
49.547.2
2025.12
45.641.2
2025.12
44.634.9
2026.03
-68.1
-69.8
-71.2
-71.2
2026.03
-70.9