List your company

Fact Extraction and Claim Verification on HoVer (test)

63.2RecallFLOWBOT
45.31249.95654.659.244Apr 29, 2026

Evaluation results

MethodLinks
FLOWBOTModel=GPT-4.1 mini2026.0463.2
GEPA+MergeModel=GPT-4.1 mini2026.0456.67
GEPAModel=GPT-4.1 mini2026.0451.67
MIPROv2Model=GPT-4.1 mini2026.0448.33
TextGradModel=GPT-4.1 mini2026.0447.67
BaselineModel=GPT-4.1 mini2026.0446.33
TraceModel=GPT-4.1 mini2026.0446