Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.26Overall Accuracy
42
Jun 5, 2026
70.12Overall Score
42
Jun 5, 2026
57.7F1 Score
42
Jun 2, 2026
73.2Average Accuracy
42
May 14, 2026
95.59Accuracy
42
May 8, 2026
67.8F1
42
Jun 12, 2026
85Accuracy
42
Feb 26, 2026
91.82Accuracy
42
Feb 26, 2026
65Accuracy
42
Feb 26, 2026
47.8F1
42
Jun 11, 2026
88Accuracy
42
Jun 4, 2026
62.56F1
42
Apr 23, 2026
69.44Accuracy
42
Feb 26, 2026
89.5Recall
42
Mar 18, 2026
88.23Truthful*Inf Score
42
Feb 26, 2026
91.3Accuracy
41
Apr 27, 2026
79.89Accuracy
41
May 11, 2026
81.05Accuracy
41
Mar 12, 2026
83.67Accuracy
40
Jun 25, 2026
1.73Average Rank
40
May 26, 2026
2,727Correlation
40
May 20, 2026
85Accuracy
40
May 12, 2026
0.235Empirical Error Rate (EER)
40
Feb 26, 2026
23.47EER
40
Feb 26, 2026
21.96Score
40
Feb 27, 2026