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

Competition-style Proof and Derivation on AIME 21-24

86.2Accuracy

Raw CoT

1.64823.59945.5567.501Jun 28, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.06
86.28,190
2026.06
82.52,979
2026.06
81.33,266
2026.06
79.63,946
2026.06
77.43,545
2026.06
46.84,572
2026.06
46.14,234
2026.06
45.22,038
2026.06
43.72,361
2026.06
38.52,453
2026.06
382,637
2026.06
37.33,025
2026.06
36.72,805
2026.06
32.52,912
2026.06
30.22,610
2026.06
6.21,035
2026.06
6.11,705
2026.06
5.81,205
2026.06
5.31,051
2026.06
4.91,041