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

Factual Reasoning on TruthfulQA MCQ

39.33MCQ Accuracy

STAR-1

-1.27169.269219.8130.3508Jul 29, 2025
Updated 2mo ago

Evaluation Results

MethodLinks
2025.07
39.33
2025.07
38.89
2025.07
38.74
2025.07
37.43
2025.07
21.93
2025.07
21.64
2025.07
20.61
2025.07
19.88
2025.07
18.57
2025.07
12.28
2025.07
9.8
2025.07
8.92
2025.07
6.48
2025.07
5.55
2025.07
4.68
2025.07
3.22
2025.07
0.44
2025.07
0.29