List your company

Open-ended Question Answering on TruthfulQA Freeform

63.94Benign F1PARASITE
54.569657.002359.43561.8677May 22, 2025

Evaluation results

MethodLinks
PARASITEModel=4o-mini2025.0563.9463.9252.552.5
PARASITEModel=3.5-Turbo2025.0554.9354.938484