Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
73F1 Score
6
Feb 26, 2026
73F1
6
Feb 26, 2026
31.4EM (ReAct)
6
Feb 26, 2026
90.3Precision
6
Feb 26, 2026
46.45Overall EM
6
Feb 26, 2026
55.12Accuracy
6
Feb 26, 2026
72.2Exact F1
6
Feb 26, 2026
46.5Exact F1
6
Feb 26, 2026
58.4Accuracy (0-shot)
6
Feb 26, 2026
96.4Accuracy
6
Feb 26, 2026
74.8FT F1
6
Feb 26, 2026
81EM
6
Feb 26, 2026
9.7BLEU-1
6
Feb 26, 2026
27.9B-1 Score
6
Feb 26, 2026
69.5Accuracy (EN)
6
Feb 26, 2026
84.1EM
6
Feb 26, 2026
56.2In-Table EM
6
Feb 26, 2026
54.3In-Table EM
6
Feb 26, 2026
86.1Accuracy
6
Feb 27, 2026
80.4Score
6
Feb 26, 2026
81.3Score
6
Feb 26, 2026
54.2Score
6
Feb 26, 2026
45.5Score
6
Feb 26, 2026
67Score
6
Feb 26, 2026
58Score
6
Feb 26, 2026