2WikiMultiHopQA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
2WikiMultihopQA
81.5Pass@1 Accuracy
4
2WikiMultiHopQA (500 randomly chosen questions)
3.47BM25 Queries
4
2WikiMultihopQA 56K context
73.4F1 Score
4
2WikiMultihopQA 28K context
73.4F1
4
2WikiMultihopQA 14K context
75F1 Score
4
2WikiMultihopQA blind (test)
0.885Answer EM
4
2WikiMultihopQA LongBench (test)
36String Match
3
2WikiMultiHopQA
87.8CDR
3
2WikiMultihopQA
37.99EM
3
2WikiMultiHopQA Large-scale corpus (KILT)
71.3EM
3
2WikiMultihopQA Search-o1 framework (50% held-out test)
39.2Accuracy
3
2WikiMultihopQA
89.31Accuracy
3
2WikiMultihopQA (dev)
99.93EM
2