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

Truthful Question Answering on TruthfulQA (Accuracy)

56.8Accuracy (TruthfulQA)

LLaDA

18.00828.07938.1548.221Apr 17, 2025Jun 24, 2025Sep 1, 2025Nov 9, 2025Jan 16, 2026Mar 26, 2026Jun 3, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
56.8
2026.05
54.6
2025.09
53.9
2026.05
53.5
2025.09
53.4
2026.05
52.5
2026.05
49.8
2026.05
49.8
2026.06
49.76
2026.06
49.72
2026.06
49.02
2026.05
48.6
2026.06
48.56
2026.06
47.49
2026.06
47.2
2026.05
46.9
2025.09
46.7
2026.05
44.4
2025.04
39.74
2025.04
39.06
2025.04
37.93
2025.04
37.67
2025.04
37.6
2025.04
36.86
2026.05
36.1
2025.04
32.22
2026.03
28.6
2026.03
27.7
2026.03
26.8
2026.03
26.4
2026.03
26
2026.03
25.1
2026.03
23.8
2026.03
23.6
2026.05
23.3
2026.03
22.4
2026.05
19.5