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

Reasoning Correctness Evaluation on RLVR Multi-subject

0Average FPR (%)

Master-RM 7B

-2.64815.22633.150.974Jul 11, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.07
0-0
2025.07
0.1-0.2
2025.07
0.1-0.5
2025.07
0.7-4.1
2025.07
0.9-3.4
2025.07
4.6-26.7
2025.07
9-15.7
2025.07
10.4-28.9
2025.07
19.6-54.1
2025.07
51.4-70.5
2025.07
55-73.8
2025.07
66.2-79.7
2025.07
-0-
2025.07
-0-
2025.07
-0-
2025.07
-0-
2025.07
-0-
2025.07
-0-
2025.07
-0-
2025.07
-0-
2025.07
-0-
2025.07
-0-