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

Mathematical Reasoning on Math Vista

65.3Accuracy

Base

32.12440.73749.3557.963May 11, 2026May 20, 2026May 30, 2026Jun 8, 2026Jun 18, 2026Jun 27, 2026Jul 7, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2026.05
65.381.95100
2026.05
6278.9896.38
2026.07
60.7--
2026.07
60.4--
2026.07
59.7--
2026.07
58.5--
2026.05
5777.194.09
2026.05
5369.4984.8
2026.05
52.876.8193.74
2026.05
52.473.2589.39
2026.05
52.175.0991.64
2026.05
49.863.7277.75
2026.05
49.863.7277.75
2026.05
48.966.1580.73
2026.05
47.966.9781.72
2026.05
45.650.7361.91
2026.05
45.160.8474.24
2026.07
44.8--
2026.05
4455.1567.3
2026.05
43.451.5462.9
2026.07
42.3--
2026.05
39.243.7153.34
2026.07
33.4--