Factual A/B test
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
87Pairwise Accuracy
3
May 20, 2026
97Pairwise Accuracy
3
May 20, 2026
82Pairwise Accuracy
3
May 20, 2026
83Pairwise Accuracy
3
May 20, 2026
73Pairwise Accuracy
3
May 20, 2026