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

Robustness Evaluation on AIME

0FPR

Master-RM

-4235077Dec 19, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
0
2025.12
0
2025.12
0
2025.12
0
2025.12
0
2025.12
2.25
2025.12
2.25
2025.12
32.69
2025.12
37.41
2025.12
41.59
2025.12
81.78
2025.12
86.07
2025.12
87.25
2025.12
93.35
2025.12
96.46
2025.12
99.25
2025.12
99.25
2025.12
100
2025.12
100
2025.12
100