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

Truthfulness on TruthfulQA (Score, Step)

41.98Truthfulness Score

AHD

34.970436.790238.6140.4298Apr 10, 2026Apr 11, 2026Apr 12, 2026Apr 13, 2026Apr 14, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.04
41.9872.21
2026.04
41.78256
2026.04
41.4952.91
2026.04
41.4983.93
2026.04
41.37104.26
2026.04
41.27256
2026.04
40.8868.5
2026.04
40.7653.25
2026.04
40.39256
2026.04
40.39256
2026.04
40.3967.22
2026.04
40.3985.56
2026.04
36.61-
2026.04
36.33-
2026.04
35.53-
2026.04
35.24-