Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
47Accuracy
3
Jun 15, 2026
11.9F1 Score
3
Jun 11, 2026
14.3F1 Score
3
Jun 11, 2026
64.1Accuracy
3
Jun 11, 2026
66R Score
3
Jun 8, 2026
76R (%)
3
Jun 8, 2026
82.3R (%)
3
Jun 8, 2026
11Correct Count
3
Jun 5, 2026
43Factual Correctness Precision (mean)
3
Jun 5, 2026
19.2F1
3
Jun 5, 2026
80.8Accuracy
3
Jun 4, 2026
68.23Accuracy
3
Jun 4, 2026
49.45Accuracy (ARC Easy)
3
Jun 4, 2026
79.1Hits@1
3
Jun 4, 2026
88.7Hits@1
3
Jun 4, 2026
64.29Cost Reduction
3
Jun 4, 2026
71.43Cost Reduction
3
Jun 4, 2026
62.9Overall EM
3
Jun 2, 2026
37.99EM
3
May 29, 2026
34.68EM
3
May 29, 2026
66.76EM
3
May 29, 2026
98Accuracy
3
May 28, 2026
99.8Accuracy
3
May 28, 2026
79.1Mean@16
3
May 28, 2026
55.9Mean@16
3
May 28, 2026