Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
70.4Accuracy (AC)
8
May 26, 2026
55.4Accuracy (AC)
8
May 26, 2026
64.6Judged Accuracy (AC)
8
May 26, 2026
78.3Accuracy (AC)
8
May 26, 2026
35.13F1 Score
8
May 25, 2026
30.2Accuracy
8
May 21, 2026
34Accuracy
8
May 21, 2026
68.2Accuracy (TQA)
8
May 21, 2026
49.4Accuracy
8
May 21, 2026
100AR (%)
8
May 21, 2026
60.8Accuracy
8
May 21, 2026
93.2Accuracy
8
May 21, 2026
91.41P@8
8
May 20, 2026
52.5Accuracy
8
May 20, 2026
82.2Accuracy
8
May 20, 2026
64.3Accuracy
8
May 20, 2026
46.5Accuracy
8
May 20, 2026
52.8Accuracy
8
May 20, 2026
57.3Accuracy
8
May 20, 2026
67Accuracy
8
May 20, 2026
37.8Accuracy
8
May 19, 2026
79.24Accuracy
8
May 19, 2026
69.6Accuracy
8
May 15, 2026
35ROUGE-1
8
May 14, 2026
0.83Wall-clock Time (hours)
8
May 12, 2026