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

Multiple-Choice Question Answering on TruthfulQA MC1

76.2MC1 Accuracy

EdgeJury

28.04840.54953.0565.551Oct 2, 2023Mar 2, 2024Aug 1, 2024Dec 31, 2024Jun 1, 2025Oct 31, 2025Apr 2, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2025.12
76.2
2025.12
72.1
2023.10
69.8
2023.10
69.8
2025.12
68.1
2025.12
67.8
2025.12
66.4
2023.10
65.9
2025.12
62.8
2023.10
60.7
2023.10
60.6
2023.10
59.2
2023.10
58.9
2023.10
58.2
2023.10
56.8
2023.10
55
2023.10
54.2
2023.10
53.1
2023.10
50.3
2026.02
49.95
2023.10
49.6
2026.02
48.84
2023.10
47.2
2026.04
43.38
2026.04
43.27
2026.04
42.95
2026.02
38.53
2026.02
37.7
2026.02
35.99
2023.10
35.9
2026.04
35.47
2026.04
35.29
2026.04
34.79
2026.02
34.15
2026.02
33.54
2023.10
32.3
2023.10
32.2
2023.10
31
2023.10
29.9