List your company

ResearchFormerly WizWand

Factual Accuracy Estimation

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

Real-data Factual Mistral responses

Logistic Regression

51.05Original Accuracy

6

Jun 19, 2026

Real-data Factual Qwen responses

Logistic Regression

55.94Original Accuracy

6

Jun 19, 2026

Real-data Factual Gemini responses

Logistic Regression

66.37Original Accuracy

6

Jun 19, 2026

Real-data Factual GPT-5.4-mini responses

Logistic Regression

62.47Original Accuracy

6

Jun 19, 2026

Real-data Factual GPT-5.4 responses

Logistic Regression

64.39Original Accuracy

6

Jun 19, 2026