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

Correctness Prediction on TruthQA

69.12Accuracy

LOCUS

33.988843.109452.2361.3506Jan 28, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
69.12
2026.01
69.12
2026.01
67.43
2026.01
66.31
2026.01
65.82
2026.01
65.69
2026.01
62.9
2026.01
60.56
2026.01
57.89
2026.01
56.38
2026.01
51.35
2026.01
50.86
2026.01
47.09
2026.01
44.63
2026.01
40.08
2026.01
39.18
2026.01
38.04
2026.01
35.34