Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Factual Accuracy Estimation on Real-data Factual Mistral responses

51.05Original Accuracy

Logistic Regression

48.497549.7737551.0552.32625Jun 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
51.0556.115.06248
2026.06
51.0553.92.84248
2026.06
51.0559.968.91248
2026.06
51.0550.87-0.19248
2026.06
51.0556.325.27248
2026.06
51.0572.3721.31259