NQ
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
NQ
45.67Accuracy (NQ General Reasoning)
20
NQ
85.7Average Performance Score
20
NQ (test)
0.758AUROC
20
NQ-Open
29Accuracy
20
NQ BEIR
62.76nDCG@10
20
NQ
97.8Performance
20
NQ
72.74EM
20
NQ BEIR
45.36NDCG@10
19
NQ-Open
57.6EM
19
NQ (in-domain)
48.2Accuracy
19
NQ
72.8R@5
19
NQ 10K context
61.8Accuracy
19
NQ DPR 3610 questions
50EM
19
NQ
53.47Accuracy
19
NQ 128K
19Accuracy
18
NQ PIA Attack (test)
66.2Accuracy
18
NQ
62.6pass@1
18
NQ (val)
79.95Accuracy (NQ val)
18
NQ SYNTH
79Accuracy
18
NQ ID
69.3Accuracy
18
NQ
0.574Cover EM
18
NQ 100K context
0.583Accuracy
18
NQ 30K context
51.1Accuracy
18
NQ (test)
67.32Hits@1
18
NQ
50.8F1 Score
17