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

Truthfulness Evaluation on TruthfulQA (Metric: TruthfulQA)

82.6TruthfulQA Score

Council Mode

48.48857.34466.275.056Feb 17, 2026Feb 24, 2026Mar 4, 2026Mar 11, 2026Mar 19, 2026Mar 26, 2026Apr 3, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.04
82.6
2026.04
74.8
2026.04
71.2
2026.04
68.5
2026.04
65.3
2026.04
63.1
2026.02
54
2026.02
53.9
2026.02
50.7
2026.02
50.7
2026.02
50.2
2026.02
49.8