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

Mathematical Reasoning on RBench-V Math

61.4Accuracy

ATLAS

13.45625.90338.3550.797Mar 24, 2026Apr 4, 2026Apr 16, 2026Apr 27, 2026May 9, 2026May 20, 2026Jun 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
61.4
2026.06
54.5
2026.06
48.3
2026.06
43.2
2026.06
42.6
2026.06
38.6
2026.06
34.7
2026.03
30.1
2026.03
29.5
2026.03
26.7
2026.03
25.3
2026.03
25
2026.03
24.4
2026.03
23.6
2026.03
23.2
2026.03
23
2026.03
22.7
2026.03
21.8
2026.03
21.6
2026.03
21.3
2026.03
20.1
2026.03
15.9
2026.03
15.3