List your company

Fact-checking on AggreFact CNN

69.5Balanced AccGraphEval
44.33250.86657.463.934Feb 23, 2025

Evaluation results

MethodLinks
GraphEval2025.0269.5
Claude 3.5-SonnetScale=>300B2025.0268.8
GPT-4oScale=>300B2025.0266.8
GraphCheckBackbone=Qwen 72B2025.0266.5
OpenAI o1Scale=>300B2025.0265.3
MiniCheck2025.0263.7
DeepSeek-V3 671BScale=>300B2025.0263.2
GraphCheckBackbone=Llama3.3 70B2025.0262.4
GPT-4Scale=>300B2025.0260.7
AlignScore2025.0254.1
Llama3.3 70B2025.0253.5
Llama3 8B2025.0251.3
ACUEval2025.0250
Qwen2.5 72B2025.0249.9
Qwen2.5 7B2025.0245.3