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

Multimodal Mathematical Reasoning on MathVista

85.1GPS Score

Claude-4-Sonnet

33.146.660.173.6Feb 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
85.181.9
2026.02
79.3379
2026.02
77.8876.51
2026.02
7574.73
2026.02
70.6761.57
2026.02
69.2367.97
2026.02
68.7558.36
2026.02
67.3164.06
2026.02
66.9365.12
2026.02
65.3853.38
2026.02
60.5855.16
2026.02
57.6951.6
2026.02
43.7544.48
2026.02
42.7939.86
2026.02
35.133.45