2WikiMultiHopQA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
2WikiMultihopQA
36.8EM
27
2WikiMultiHopQA
59.1EM
26
2WikiMultihopQA
62.5Accuracy
25
2WikiMultihopQA
45.65Exact Match (EM)
24
2WikiMultiHopQA online Google Search API (test val)
63.5Exact Match
24
2WikiMultiHopQA offline Wiki-18 (test val)
43.6Exact Match
24
2WikiMultiHopQA N=200
77Judge EM
24
2WikiMultihopQA
100Precision @ K=2
23
2WikiMultiHopQA
96.86Precision
22
2WikiMultiHopQA Full
87.5Accuracy (C)
22
2WikiMultihopQA
5.1EM
21
2WikiMultiHopQA v1 (test)
85R@2E
21
2WikiMultihopQA
46EM
20
2WikiMultihopQA
64EM
20
2WikiMultihopQA
89.7LLM-Acc
20
2WikiMultiHopQA (test val)
35.44EM
20
2WikiMultiHopQA (held-out)
77.4F1 Score
18
2wikiMultiHopQA
76.1F1 Score
18
2WikiMultiHopQA
78SR
17
2WikiMultiHopQA (dev test)
81.5F1 Score
17
2WikiMultiHopQA (2WikiMQA) (official evaluation)
31.8Exact Match (EM)
17
2WikiMultiHopQA
67.1Containment Accuracy
16
2WikiMultihopQA (val)
24.3EM
16
2WikiMultiHopQA (test val)
43.9Exact Match (EM)
16
2WikiMultihopQA
59.3EM
16