Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
75.7Compressed Accuracy
2
Mar 18, 2026
57.3Normalized Log Accuracy
2
Mar 18, 2026
83Normalized Log Accuracy
2
Mar 18, 2026
38.9Log Accuracy
2
Mar 18, 2026
64.8Accuracy
2
Mar 17, 2026
35.6Accuracy
2
Mar 17, 2026
79.8Accuracy
2
Mar 17, 2026
51.1Accuracy
2
Mar 17, 2026
75.1Accuracy
2
Mar 17, 2026
28.6Accuracy
2
Mar 12, 2026
25.34Score
2
Mar 12, 2026
16.1NQ Score
2
Mar 4, 2026
272LEARNED Score
2
Feb 27, 2026
321LEARNED Count
2
Feb 27, 2026
625Learned Count
2
Feb 27, 2026
1,893Learned Count
2
Feb 27, 2026
77.93Long Answer F1
2
Feb 26, 2026
100ISR
2
Feb 26, 2026
42.6BLEU Accuracy
2
Feb 26, 2026
37F1 Score
2
Feb 26, 2026
51F1 Score
2
Feb 26, 2026
65F1 Score
2
Feb 26, 2026
59.4F1 Score
2
Feb 26, 2026
1.47Inference Cost (USD)
2
Feb 26, 2026
0.026MAE
2
Feb 26, 2026