Memory-augmented Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
49.61Token F1
25
Jun 4, 2026
92.6Accuracy (Temporal)
25
Jun 4, 2026
36.91Mean Token-F1
23
Jun 1, 2026
44.79Mean Token F1
23
Jun 1, 2026
20.77Token F1
23
Jun 1, 2026
34.1Mean Token F1
23
Jun 1, 2026
92.9SSU Score
10
May 29, 2026
97.2Accuracy
6
Jun 23, 2026
96.4Accuracy
6
Jun 23, 2026
73.39Accuracy (Single)
3
Apr 24, 2026
100RelAcc
2
Apr 21, 2026