Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
49.12EM Accuracy
24
Mar 10, 2026
42.9Exact Match Accuracy (EM)
24
Mar 10, 2026
75.4EM Accuracy
24
Mar 10, 2026
63.2Accuracy
24
Jun 5, 2026
91.6Accuracy
24
Feb 26, 2026
57.9EM
24
Jun 9, 2026
88.59Accuracy
24
Feb 26, 2026
66Avg. PS Shift (%)
24
Feb 26, 2026
31.03Accuracy
24
Feb 26, 2026
63.34Accuracy
24
Feb 26, 2026
90.2Accuracy
24
Feb 26, 2026
84.45Accuracy
24
Feb 26, 2026
61.8Accuracy
24
Feb 26, 2026
85.79Accuracy
24
Feb 26, 2026
58.7EM
24
Feb 26, 2026
87.7MRR
24
Feb 26, 2026
78.6Accuracy
24
Feb 26, 2026
49.8Accuracy
24
Feb 26, 2026
9.7MR
24
Feb 26, 2026
7.7Mean Rank
24
Feb 26, 2026
63.1Accuracy
23
Jul 9, 2026
79.66Accuracy (WebQ)
23
Jul 9, 2026
87.6Accuracy
23
May 14, 2026
93.95F1 Score
23
May 15, 2026
78.38Accuracy
23
Jul 1, 2026