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

Multimodal Mathematical Reasoning on MathVista 14 (1000)

90.2Macro Score

Qwen3.5-397B-A17B*

50.57660.86371.1581.437May 10, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.05
90.2--
2026.05
88.5--
2026.05
86.3--
2026.05
84.9--
2026.05
81.9--
2026.05
81.2--
2026.05
76.692.3190.38
2026.05
76.692.7990.8
2026.05
75.887.585.77
2026.05
74.888.9486.19
2026.05
73.483.6582.43
2026.05
72.887.0284.52
2026.05
69.470.6768.62
2026.05
68.567.7966.53
2026.05
67.970.1969.87
2026.05
63.278.8575.73
2026.05
63.165.3864.02
2026.05
61.864.964.85
2026.05
61.753.8554.81
2026.05
60.153.8454.18
2026.05
59.650.4850.63
2026.05
52.157.2157.74