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

Truthfulness on TruthfulQA 4 options (test)

80.1Accuracy (ACC)

KP

54.6261.23567.8574.465Sep 28, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
80.11000
2025.09
76.31000
2025.09
73.577.60.46
2025.09
67.878.80.6
2025.09
65.672.90.48
2025.09
64.167.30.95
2025.09
62.367.20.6
2025.09
61.965.10.97
2025.09
61.163.50.98
2025.09
60.6640.99
2025.09
58.861.81.01
2025.09
58.561.31.02
2025.09
56.762.10.63
2025.09
55.661.60.76