Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
4.65ROUGE Score
6
Mar 13, 2026
0.409ROUGE
6
Mar 13, 2026
44.35ROUGE Score
6
Mar 13, 2026
33MC1 Score
6
Mar 12, 2026
82.7Accuracy
6
Mar 10, 2026
88.1Accuracy
6
Mar 10, 2026
59.8EM
6
Mar 6, 2026
45.7Metric 9 (GROWOVER-QA)
6
Feb 27, 2026
28.2QA Score 9
6
Feb 27, 2026
39.4QA Score 9
6
Feb 27, 2026
83.9English QA Score
6
Feb 27, 2026
24,686.84Prefill Throughput (tok/s)
6
Feb 26, 2026
53.56Score
6
Feb 26, 2026
84.6Accuracy
6
Feb 26, 2026
83Accuracy
6
Feb 26, 2026
36.982WQA Score
6
Feb 26, 2026
0.66d'type2
6
Feb 26, 2026
117d'type2 Score
6
Feb 26, 2026
0.278Inference Cost (USD)
6
Feb 26, 2026
19.9Accuracy
6
Feb 26, 2026
44.6L Score
6
Feb 26, 2026
30.6EM
6
Feb 26, 2026
74.86BoolQ Accuracy
6
Feb 26, 2026
61.5Accuracy
6
Feb 26, 2026
72.17Accuracy
6
Feb 26, 2026