Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
67.99Precision
26
Apr 14, 2026
58.13Precision
26
Apr 14, 2026
87.2Precision
26
Apr 14, 2026
2.916Speedup Ratio
26
Apr 8, 2026
70.7Accuracy (Acc)
26
Mar 10, 2026
87.7Accuracy
26
Feb 26, 2026
59F1 Score
26
Mar 25, 2026
38.92EM
26
Feb 26, 2026
78.03Accuracy
26
May 14, 2026
90.4Accuracy
26
Mar 10, 2026
2,946Tokens Processed
26
Feb 26, 2026
56.94Easy Score
26
Feb 26, 2026
81.66EM
26
Feb 26, 2026
91.67F1 Score
26
Feb 26, 2026
80.2Accuracy
25
Jun 2, 2026
68.29BERTScore F1
25
May 19, 2026
67.6BERTScore F1
25
May 19, 2026
73.5F1 Score
25
Apr 15, 2026
88.33Accuracy (Avg)
25
May 27, 2026
82.5Accuracy
25
Mar 4, 2026
58.9Accuracy
25
Jun 2, 2026
92.6Accuracy
25
Jun 4, 2026
80.48Accuracy
25
Mar 16, 2026
78.91Accuracy
25
Apr 27, 2026
64.3Accuracy (Table)
25
Feb 26, 2026