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

Truthfulness on TruthfulQA (accuracy)

72.36Truthfulness Accuracy

AgentRevive

16.761631.195845.6360.0642Jul 27, 2025Sep 21, 2025Nov 16, 2025Jan 11, 2026Mar 8, 2026May 3, 2026Jun 28, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.05
72.36
2026.05
70.15
2026.05
69.23
2026.05
68.7
2026.05
68.44
2026.05
66.63
2026.05
66.05
2026.05
65.89
2026.05
65.49
2026.05
65.16
2026.05
64.99
2026.05
64.7
2026.05
64.34
2025.07
63.7
2026.05
63.7
2026.05
63.62
2026.05
62.83
2026.05
62.43
2026.05
61.78
2025.07
60.7
2026.05
60.7
2026.05
60.14
2026.05
59.88
2026.05
59.25
2025.07
59.2
2026.05
59.07
2025.07
58.2
2026.05
58.2
2026.05
57.59
2025.07
57.1
2025.07
56.4
2025.07
56.2
2025.07
55.9
2026.04
54.85
2025.07
53.7
2026.05
53.7
2026.04
53.69
2026.06
52.5
2026.06
52.5
2026.06
51.7
2026.06
51.7
2025.07
51.5
2026.05
51.5
2026.04
49.78
2026.06
49.1
2026.04
48.88
2026.04
48.03
2026.04
47.85
2026.04
47.36
2026.06
47.1
2026.06
46.9
2026.04
46.85
2026.06
46.6
2026.04
46.58
2026.06
46.1
2026.04
45.88
2026.04
45.77
2026.06
45.6
2026.06
44.6
2026.06
43.5
2026.04
43.42
2026.06
43.2
2026.04
43.02
2026.06
41.5
2026.06
41.3
2026.06
39.9
2026.06
39.9
2026.06
39.8
2026.04
36.03
2026.06
21.4
2026.06
21.3
2026.06
20.4
2026.06
20.3
2026.06
20.1
2026.06
20
2026.06
19.5
2026.06
19.5
2026.06
18.9