Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
63.1AUROC
6
Feb 26, 2026
65.6Accuracy
6
Feb 26, 2026
64.9Accuracy
6
Feb 26, 2026
64.5Accuracy
6
Feb 26, 2026
75.8Accuracy
6
Feb 26, 2026
82.9Accuracy
6
Feb 26, 2026
81.4Accuracy
6
Feb 26, 2026
74.3Accuracy
6
Feb 26, 2026
66.9Accuracy
6
Feb 26, 2026
66.9Accuracy
6
Feb 26, 2026
66.9Accuracy
6
Feb 26, 2026
60FR Recall (3-gram)
6
Feb 26, 2026
29Bio QA Recall
6
Feb 26, 2026
63.3P@1
6
Feb 26, 2026
3.97Match Count (#MAT)
6
Feb 26, 2026
75.1SQA^I Score
6
Feb 26, 2026
5.18MAPE
6
Feb 27, 2026
1.64MAPE
6
Feb 27, 2026
3.61MAPE (%)
6
Feb 27, 2026
3.48MAPE (%)
6
Feb 27, 2026
19.27Claim Recall
6
Feb 26, 2026
27.25F1 Score
6
Feb 26, 2026
88.4Accuracy
6
Jun 30, 2026
44.9Score 9
6
Feb 27, 2026
86.1F1 Score
6
Feb 26, 2026