Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.5Accuracy Delta
12
Apr 7, 2026
87.7F1 Score
12
Feb 26, 2026
73F1
12
Feb 26, 2026
47.2Hits@1
12
Feb 26, 2026
46.6Add Sent Score
12
Feb 26, 2026
50Task: 1 Supporting Fact Acc
12
Feb 26, 2026
2.01Accuracy Improvement
12
Feb 27, 2026
32.11Accuracy
12
Feb 26, 2026
75.4Accuracy
12
Feb 27, 2026
94.6Accuracy
12
Feb 27, 2026
93.5Accuracy
12
Feb 27, 2026
92.6Accuracy
12
Feb 27, 2026
98.8Activation Score
11
Jun 30, 2026
100Activation Score
11
Jun 30, 2026
100Activation
11
Jun 30, 2026
97.6Activation (Act)
11
Jun 30, 2026
37.5Accuracy
11
Jun 30, 2026
96Accuracy
11
Jun 26, 2026
87.8Accuracy
11
Jun 26, 2026
98.9Accuracy
11
Jun 26, 2026
100Quality (%)
11
Jun 30, 2026
26.9Accuracy
11
Jun 25, 2026
96.1Macro F1
11
Jun 24, 2026
69.19Accuracy
11
Jun 23, 2026
60.27Accuracy
11
Jun 23, 2026