Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Truthfulness Evaluation on TruthfulQA (Normalized Accuracy)

58.76Normalized Accuracy

IPO

43.4247.402551.38555.3675Dec 13, 2024Jan 8, 2025Feb 3, 2025Mar 1, 2025Mar 27, 2025Apr 22, 2025May 18, 2025
Updated 3d ago

Evaluation Results

MethodLinks
2025.05
58.76
2025.05
58.44
2025.05
58.06
2025.05
57.82
2025.05
57.76
2025.05
57.74
2025.05
57.63
2025.05
57.34
2024.12
44.22
2024.12
44.01