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

Truthful Question Answering on TruthfulQA MC2 (MC2 %)

56.46MC2 Accuracy

HRTN

38.821643.400847.9852.5592Jul 24, 2025Sep 2, 2025Oct 12, 2025Nov 22, 2025Jan 1, 2026Feb 10, 2026Mar 23, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2025.07
56.46
2025.07
55.95
2025.07
55.81
2025.07
55.77
2025.07
55.34
2025.07
55.21
2025.07
54.81
2025.07
54.73
2025.07
54.55
2025.07
54.5
2025.07
54.46
2025.07
53.76
2025.07
53.68
2025.07
53.6
2025.07
53.47
2025.07
53.36
2025.07
53.05
2025.07
52.91
2025.07
52.76
2025.07
51.78
2025.07
50.46
2025.07
50.25
2025.07
49.01
2025.07
48.53
2025.07
47.33
2026.03
47.2
2025.07
46.91
2026.03
45.9
2025.07
45.54
2026.03
45.5
2026.03
45.5
2026.03
45.4
2026.03
44.1
2026.03
44.1
2025.07
43.88
2026.03
42.6
2026.03
42.4
2026.03
42.4
2026.03
41
2026.03
41
2026.03
40.9
2026.03
40.4
2026.03
40.3
2026.03
40.2
2026.03
39.8
2026.03
39.5