Multi-hop Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
45.5Exact Match (EM)
14
May 14, 2026
16.9Exact Match
14
May 14, 2026
44.4Exact Match (EM)
14
May 14, 2026
52Exact Match Accuracy
14
May 14, 2026
62.25F1 Score
14
Apr 21, 2026
33.36F1 Score
14
Apr 21, 2026
56.91F1 Score
14
Apr 21, 2026
63.09F1 Score
14
Apr 21, 2026
35Exact Match (EM)
14
Apr 21, 2026
0.601EM
14
Apr 21, 2026
45.2Accuracy
14
Mar 13, 2026
22.1Accuracy
14
Mar 13, 2026
43.6Accuracy (%)
14
Mar 13, 2026
46.8Accuracy
14
Mar 13, 2026
12.9F1 Score
14
Feb 26, 2026
79.69F1 Score
14
Feb 26, 2026
71.93F1 Score
14
Feb 26, 2026
74.83F1 Score
14
Feb 26, 2026
81.01F1 Score
14
Feb 26, 2026
52.94F1 Score
14
Feb 26, 2026
55.49LLM Judge Score
14
Feb 26, 2026
29.6Accuracy R
14
Feb 26, 2026
68.8Accuracy (R)
14
Feb 26, 2026
69.8Accuracy (Response)
14
Feb 26, 2026
60.4ACC_R
14
Feb 26, 2026