Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
85.16Exact Match (EM)
9
May 15, 2026
96.09Exact Match (EM)
9
May 15, 2026
14Leakage Error
9
May 12, 2026
5.7Leakage Error
9
May 12, 2026
1.4Leakage Error
9
May 12, 2026
46.9Accuracy
9
Jun 23, 2026
46.4EM
9
May 8, 2026
100Accuracy
9
May 7, 2026
25.6Alias-Substring Accuracy
9
May 6, 2026
39.8Accuracy
9
May 6, 2026
53.13Accuracy
9
May 1, 2026
92.22Accuracy
9
May 1, 2026
31.5HalRate
9
Apr 28, 2026
75.7Accuracy
9
Apr 24, 2026
70.6Token F1
9
Apr 21, 2026
23EM
9
Apr 15, 2026
62.2Exact Match (EM)
9
Apr 15, 2026
39.4Exact Match (EM)
9
Apr 15, 2026
20.7Accuracy
9
Apr 14, 2026
45.46Score
9
Apr 8, 2026
1.3Accuracy Delta
9
Apr 7, 2026
31.1Accuracy
9
Apr 7, 2026
63.5Accuracy
9
Apr 7, 2026
71.8Accuracy
9
Apr 7, 2026
29.01LM Score
9
Apr 7, 2026