List your company

Fact Verification on FEVER (Macro F1)

91Macro F1GPT-4o-mini
75.71279.68183.6587.619Jun 29, 2026

Evaluation results

MethodLinks
GPT-4o-miniOutput format=struct2026.0691
MiniCheck-FT5Output format=binary2026.0687.1
SEVA-GRPO (3B)Output format=struct, Size=3B2026.0684.9
SEVA-SFT (3B)Output format=struct, Size=3B2026.0676.3