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

Mathematical Reasoning on MathVerse mini (test)

66.9Accuracy

Human

7.72423.08738.4553.813Feb 12, 2026Feb 16, 2026Feb 21, 2026Feb 26, 2026Mar 2, 2026Mar 7, 2026Mar 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
66.9
2026.02
57.2
2026.02
56.6
2026.02
54.6
2026.02
54.5
2026.03
50.5
2026.02
49.3
2026.02
47.8
2026.03
41.4
2026.02
41.2
2026.03
37.8
2026.03
35.5
2026.03
34.7
2026.03
33.9
2026.03
33.3
2026.03
33.3
2026.03
32.5
30.8
2026.03
26
2026.03
22.4
2026.03
21.4
2026.03
18.4
2026.03
17.3
2026.03
12.9
2026.03
12.4
2026.03
10