Multi-hop Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
48.8EM
1
Feb 26, 2026
4.9# Search
1
Feb 27, 2026
3.2Search Count
1
Feb 27, 2026
2.7# Search
1
Feb 27, 2026
2.1# Search Steps
1
Feb 27, 2026
1.3Avg Search Steps
1
Feb 27, 2026
0.823Accuracy
1
Feb 26, 2026
—
—EM
0
Feb 26, 2026
—
—EM
0
Feb 26, 2026
—
—EM
0
Feb 26, 2026
—
—EM
0
Feb 26, 2026
—
—EM
0
Feb 26, 2026