List your company

Fact Verification on TrendFact (test)

78.98Accuracyo1-preview
55.652861.708967.76573.8211Oct 19, 2024

Evaluation results

MethodLinks
o1-previewEvidence Condition=Gold Evidence2024.1078.9875.1675.1375.72
DeepSeek-R1Evidence Condition=Gold Evidence2024.1077.9272.5673.7272.64
GPT-4.1Evidence Condition=Gold Evidence2024.1072.2969.6869.0272.88
QwQ-32B-PreviewEvidence Condition=Gold Evidence2024.1065.3161.7663.6865.53
Qwen-72B-instructEvidence Condition=Gold Evidence2024.1065.1460.5666.9763.65
DeepSeek-V3Evidence Condition=Gold Evidence2024.1063.7460.3166.0963.96
CLAIMDECOMPEvidence Condition=Gold Evidence2024.1059.3556.8656.6559.41
PROGRAM-FCEvidence Condition=Gold Evidence2024.1056.5554.0554.1756.62