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

Factual Accuracy Estimation on Real-data Factual Gemini responses

66.37Original Accuracy

Logistic Regression

63.051564.7107566.3768.02925Jun 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
66.3759.14-7.2283
2026.06
66.3762.22-4.1583
2026.06
66.3765.29-1.0883
2026.06
66.3754.91-11.4583
2026.06
66.3766.03-0.3483
2026.06
66.3769.212.8594