Question Answering Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
1.46Factual Accuracy
10
May 20, 2026
1.66Factual Accuracy
10
May 20, 2026
1.75Factual Accuracy
10
May 20, 2026
0.872Spearman Correlation
6
Mar 11, 2026
95.6CS
6
Mar 11, 2026
91.7CS Metric
6
Mar 11, 2026