2WikiMultiHopQA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
2WikiMultiHopQA
82.1EM
559
2WikiMultiHopQA (test)
73.9EM
247
2WikiMultihopQA (test)
78.9F1
113
2WikiMultihopQA
47.7EM
107
2WikiMultiHopQA Out-Of-Distribution (OOD)
74.2Accuracy
72
2WikiMultiHopQA (test)
88Per-query Final Recall
63
2WikiMultiHopQA in-domain
62.6F1 Score
57
2WikiMultiHopQA (Out-Of-Distribution)
63.9Accuracy
54
2WikiMultiHopQA
43Exact Match
50
2WikiMultihopQA
56.46F1 Score
45
2WikiMultiHopQA
70.3String Accuracy
44
2WikiMultiHopQA (val)
69.3Exact Match (EM)
44
2WikiMultiHopQA
81.5Accuracy
38
2WikiMultihopQA
60EM
36
2WikiMultihopQA
60EM
36
2WikiMultiHopQA (dev)
88.658Exact Match Accuracy
36
2WikiMultihopQA (test)
97.2R@5
33
2WikiMultihopQA
100Guard Rate
32
2WikiMultihopQA LongBench
59.73F1 Score
32
2WikiMultiHopQA
65.9Token F1 Score
30
2WikiMultihopQA
0.6Exact Match (EM)
28
2WikiMultiHopQA
65.04F1 Score
28
2WikiMultiHopQA
48.3EM
28
2WikiMultiHopQA (OOD)
0Degeneration Count
27
2WikiMultiHopQA (OOD)
2.21Exact Match (EM)
27