List your company

Question Answering on TruthfulQA (Hallucination, Accuracy)

55.6AccuracyCAROL
10.98422.56734.1545.733May 26, 2026

Evaluation results

MethodLinks
CAROLModel=GPT–5–nano, Latency (s)=164.8 ± 1.35, Cost ($)=0.1463 ± 0.0032026.0555.625.7
CAROLModel=Llama–3.1–8B, Latency (s)=194.3 ± 1.602026.055434.8
RAGModel=GPT–5–nano, Latency (s)=119.2 ± 1.10, Cost ($)=0.2933 ± 0.0042026.0535.6—
RAGModel=Llama–3.1–8B, Latency (s)=120.9 ± 1.252026.0512.7—