Multi-hop Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.58Average Inference Time (s)
13
May 28, 2026
37.1OSR
13
Apr 21, 2026
33.9OSR Score
13
Apr 21, 2026
29.39Accuracy
13
Feb 26, 2026
58.8String Success Rate
13
Feb 26, 2026
0.312Set Accuracy
13
Feb 26, 2026
77.3Accuracy
12
Jun 18, 2026
34.2Exact Match
12
Jun 16, 2026
69.9F1 Score
12
Jun 5, 2026
51.3EM
12
Jun 4, 2026
3.28Speedup Factor
12
Jun 2, 2026
3.55Speedup
12
Jun 2, 2026
3.77Speedup Factor
12
Jun 2, 2026
55.1Top-5 Accuracy
12
Jun 1, 2026
84.2Top-5 Accuracy
12
Jun 1, 2026
82Top-5 Accuracy
12
Jun 1, 2026
47.9EM
12
May 28, 2026
0.673Exact Match (EM)
12
Apr 30, 2026
70.2EM
12
Apr 30, 2026
61.63F1 Score
12
Apr 28, 2026
82Pass@1
12
Apr 14, 2026
60.8Pass@1
12
Apr 14, 2026
58.7CEM (%)
12
Apr 14, 2026
34.1CEM (%)
12
Apr 14, 2026
71.7CEM (%)
12
Apr 14, 2026