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

Mathematical Reasoning on AIME 24 (Acc@8, Pass@8)

41.6Accuracy@8

PACED Forward KL

-1.6649.56820.832.032Mar 10, 2026Mar 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
41.6-
2026.03
39.8-
2026.03
39.5-
2026.03
35.9-
2026.03
28.7-
2026.03
3.3320
2026.03
2.513.33
2026.03
1.676.67
2026.03
1.2510
2026.03
0.833.33
2026.03
0.423.33
2026.03
0.423.33
2026.03
00
2026.03
00