List your company

Untargeted Question Answering on TriviaQA (Benign/Malicious/Delta Metrics)

76.66Benign F1AAP
60.373664.601868.8373.0582May 22, 2025

Evaluation results

MethodLinks
AAPModel=4o-mini2025.0576.6665.4194.4891.21-17.82-25.8
PARASITEModel=4o-mini2025.0571.4459.1652.4448.641910.52
ManualModel=3.5Turbo2025.0569.1551.5299.5599.55-30.4-48.03
ManualModel=4o-mini2025.0568.2251.5699.2899.09-31.06-47.53
AAPModel=3.5Turbo2025.0566.9349.5896.5796.36-29.64-46.78
PARASITEModel=3.5Turbo2025.056140.0969.4764.55-8.47-24.46