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

Reasoning Correctness Evaluation on Naturalreasoning

0.7Average FPR

Master-RM 7B

-2.59219.62941.8564.071Jul 11, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.07
0.7-2.9
2025.07
2.6-11.3
2025.07
3.6-5.4
2025.07
4.8-13.6
2025.07
5.2-11.5
2025.07
6.1-28.6
2025.07
15.2-23.2
2025.07
16.1-37.6
2025.07
20.2-40.6
2025.07
62.3-72.8
2025.07
76.6-82.9
2025.07
83-86.7