List your company

Question Answering on PopQA (CF, EM, F1)

94.27Correct First (CF)FIDES
62.633270.846679.0687.2734Jun 4, 2026

Evaluation results

MethodLinks
FIDESModel=LLaMA3-70B2026.0694.2754.1263.45
FIDESModel=LLaMA2-13B2026.0690.3542.9244.86
AdaCADModel=LLaMA3-70B2026.0689.1542.9549.32
CADModel=LLaMA3-70B2026.0686.5431.0235.12
AdaCADModel=LLaMA2-13B2026.0678.4335.2639.92
Standard RAGModel=LLaMA3-70B2026.0675.8239.4343.06
CADModel=LLaMA2-13B2026.0670.1528.1230.54
Standard RAGModel=LLaMA2-13B2026.0663.8531.9235.46