Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
99.43Accuracy
6
May 29, 2026
95.82Accuracy
6
May 29, 2026
99.75Accuracy
6
May 29, 2026
74.5Task Success Rate (TSR)
6
May 28, 2026
82.25Task Success Rate (TSR)
6
May 28, 2026
88.25Task Success Rate (TSR)
6
May 28, 2026
100Answerability Rate
6
May 27, 2026
100Answerability Rate
6
May 27, 2026
100Answerability Rate
6
May 27, 2026
100Answerability Rate
6
May 27, 2026
79.49Accuracy
6
May 26, 2026
76.4Accuracy
6
May 22, 2026
71.6Accuracy
6
May 22, 2026
81.23Exact Match (EM)
6
May 22, 2026
58Accuracy
6
May 19, 2026
86.3Accuracy (SciQ)
6
May 18, 2026
88Entity Swap Accuracy
6
May 15, 2026
89.6Acceptance Rate
6
May 15, 2026
49.43EM
6
May 14, 2026
73.6Accuracy
6
May 13, 2026
55.94Accuracy
6
May 11, 2026
99.6Accuracy (fine_facts adversarial)
6
May 7, 2026
12.82Score
6
May 6, 2026
78Accuracy
6
May 6, 2026
64.4Accuracy
6
May 6, 2026