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

Math Reasoning on BigMath level 4

66.3Accuracy

Distillable

14.50827.95441.454.846Apr 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
66.366.476.3
2026.04
65.666.480.3
2026.04
65.166.274.8
2026.04
64.964.979.4
2026.04
63.965.279.3
2026.04
62.562.672.5
2026.04
61.561.277.3
2026.04
52.656.569
2026.04
52.351.876.3
2026.04
50.250.970.2
2026.04
49.548.876.5
2026.04
48.547.576
2026.04
48.247.475.7
2026.04
46.547.970.8
2026.04
4646.870.9
2026.04
41.339.967.4
2026.04
21.516.738
2026.04
16.5833.9