Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
27.92BLEU
9
Mar 13, 2026
21.93BLEU Score
9
Mar 13, 2026
0.555BLEU
9
Mar 13, 2026
25Error Rate (ERR)
9
Mar 13, 2026
58.08Ragas Answer Relevance
9
Mar 11, 2026
60.68Ragas Answer Relevance
9
Mar 11, 2026
54.3Accuracy (Zero-shot)
9
Mar 10, 2026
4.01Mean Accuracy
9
Mar 4, 2026
4.14Mean Accuracy Score
9
Mar 4, 2026
65.1Bio Accuracy
9
Mar 4, 2026
31.2F1 Score
9
Feb 27, 2026
72.5Fact Adherence Score
9
Feb 26, 2026
88.9Scenario 1 Score
9
Feb 26, 2026
15.1F1
9
Feb 27, 2026
23.2F1 Score
9
Feb 27, 2026
44.1F1 Score
9
Feb 27, 2026
26.7ROUGE-L
9
Feb 26, 2026
34.5Accuracy
9
Feb 26, 2026
80.86ReCoRD Score
9
Feb 26, 2026
7FDR
9
Feb 26, 2026
6.43FDR (%)
9
Feb 26, 2026
12.23Communication Time (10^3 s)
9
Feb 26, 2026
0.908AUROC
9
Feb 26, 2026
87AUROC
9
Feb 26, 2026
89Exact Match Accuracy
9
Feb 26, 2026