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

Math Reasoning on BigMath level 5

43.1Average Accuracy

Distillable

4.82814.76424.734.636Apr 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
43.142.762.6
2026.04
41.74255.1
2026.04
41.640.262.1
2026.04
39.439.252
2026.04
39.338.161.4
2026.04
38.738.152.6
2026.04
37.937.854.7
2026.04
2827.451
2026.04
2721.945.4
2026.04
25.925.446.2
2026.04
25.52450.5
2026.04
2422.549
2026.04
23.722.346.1
2026.04
23.621.249.9
2026.04
22.220.744.5
2026.04
21.619.646.4
2026.04
9.15.723.7
2026.04
6.3225.5