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

Truthfulness Evaluation on TruthfulQA (TQA Metric)

54.9TQA Score

EvoPref-Best

50.63651.74352.8553.957May 10, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
54.9
2026.05
53.3
2026.05
52.9
2026.05
52.5
2026.05
52
2026.05
51.8
2026.05
51.5
2026.05
51.1
2026.05
50.8