Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
72ACC
12
Feb 26, 2026
23Accuracy
12
Feb 26, 2026
0.094BLEU-1
12
Feb 27, 2026
69.3Accuracy
12
Mar 10, 2026
60.92EM
12
Feb 26, 2026
58EM
12
Feb 26, 2026
72.35Performance
12
Feb 26, 2026
96.22Accuracy
12
Feb 26, 2026
76Accuracy
12
Feb 26, 2026
85.75Accuracy
12
Feb 26, 2026
79.36Average Accuracy
12
Feb 26, 2026
20.1Finance Score
12
Feb 26, 2026
52.9ROUGE
12
Feb 26, 2026
76.78ROUGE
12
Mar 4, 2026
68EM
12
Feb 26, 2026
45EM
12
Feb 26, 2026
83.34F1
12
Feb 26, 2026
67.2Precision
12
Feb 26, 2026
0.705Precision
12
Feb 26, 2026
64.9Precision
12
Feb 26, 2026
0.484SAE
12
Feb 26, 2026
37.7SGL Score
12
Feb 26, 2026
0.748BLEURT
12
Feb 26, 2026
78.6Accuracy
12
Feb 26, 2026
64.26Accuracy
12
Feb 26, 2026