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

Mathematical Reasoning on AIME 25 (Pass@1, Pass@4, Pass@8)

40Pass@8

MOTAB

5.336814.335923.33532.3341May 19, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
4032.0514.58
2026.05
36.6728.3312.5
2026.05
36.6728.2413.33
2026.05
33.3324.6712.08
2026.05
33.3323.99.17
2026.05
26.6722.2911.25
2026.05
26.6722.339.59
2026.05
26.6716.575.83
2026.05
26.6718.817.5
2026.05
26.6719.527.92
2026.05
23.3317.867.92
2026.05
23.3317.146.67
2026.05
20145
2026.05
16.67--
2026.05
16.67104.58
2026.05
13.339.052.92
2026.05
6.673.330.83
2026.05
6.673.330.83
2026.05
6.674.761.67
2026.05
6.674.952.08
2026.05
6.675.241.67