List your company

Fact-checking on AVeriTeC (dev)

0.46Hu-METEOR (Q only)GPT-4o
0.23120.29060.350.4094Oct 15, 2024

Evaluation results

MethodLinks
GPT-4oPipeline configuration=full-featured2024.100.460.290.42
Llama 3.1 70BPipeline configuration=full-featured2024.100.460.270.36
GPT-4oPipeline configuration=simplified2024.100.450.280.38
GPT-4oPipeline configuration=with DeBERTa classification2024.100.450.280.36
Claude-3.5-SonnetPipeline configuration=full-featured2024.100.430.280.35
AVeriTeC baseline2024.100.240.190.09