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

Factual Accuracy Estimation on GPT-5.4-mini Responses

62.47Original Accuracy

Logistic Regression

59.346560.9082562.4764.03175Jun 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
62.4757.2-5.2688
2026.06
62.4756.79-5.6888
2026.06
62.4761.52-0.9588
2026.06
62.4753.23-9.2488
2026.06
62.4762.44-0.0388
2026.06
62.4766.073.699