Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
71.5Accuracy (MuSiQue QA)
33
Jun 29, 2026
94.44Accuracy
33
Mar 31, 2026
82.7Success Rate
33
Mar 13, 2026
94.6Accuracy
33
May 22, 2026
66.86Accuracy
32
Jul 3, 2026
100Guard Rate
32
Jul 2, 2026
100Guard Rate
32
Jul 2, 2026
100Guard Rate
32
Jul 2, 2026
95.7Accuracy
32
Jun 30, 2026
96.1Accuracy
32
Jun 30, 2026
99.6Accuracy
32
May 28, 2026
3.51Speedup
32
May 11, 2026
56.2EM
32
May 1, 2026
86.4Acc Norm
32
Apr 20, 2026
45.68Exact Match (EM)
32
May 27, 2026
41.7Accuracy
32
Apr 2, 2026
80.8Accuracy
32
Apr 2, 2026
94Accuracy
32
Apr 2, 2026
59.73F1 Score
32
May 29, 2026
92.5SQuAD Score
32
Mar 12, 2026
86.7Avg@5
32
Feb 26, 2026
53.24ARC Accuracy
32
Feb 26, 2026
0.617Accuracy
32
Feb 26, 2026
79.5F1 Score (Full)
32
Feb 26, 2026
74Accuracy
32
Feb 26, 2026