Search-augmented multi-turn question answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
48.8Exact Match (EM)
10
May 7, 2026
17.8Exact Match (EM)
10
May 7, 2026
40.2Exact Match (EM)
10
May 7, 2026
64.6Exact Match (EM) Accuracy
10
May 7, 2026
28.3Exact Match (EM) Accuracy
10
May 7, 2026