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

Fact Verification on TrendFact (test)

78.98Accuracy

o1-preview

55.652861.708967.76573.8211Oct 19, 2024
Updated 18d ago

Evaluation Results

MethodLinks
2024.10
78.9875.1675.1375.72
2024.10
77.9272.5673.7272.64
2024.10
72.2969.6869.0272.88
2024.10
65.3161.7663.6865.53
2024.10
65.1460.5666.9763.65
2024.10
63.7460.3166.0963.96
2024.10
59.3556.8656.6559.41
2024.10
56.5554.0554.1756.62