Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-hop Question Answering on HotpotQA (Ans, SF)
Loading...
78.6
Answer Accuracy (Ans)
SABA
61.752
66.126
70.5
74.874
Apr 22, 2026
Answer Accuracy (Ans)
Supporting Fact (SF)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Answer Accuracy (Ans)
Supporting Fact (SF)
SABA
Normalized inference c...
2026.04
78.6
73.5
GoT
Normalized inference c...
2026.04
78
73.2
SELF-DISC.
Normalized inference c...
2026.04
75.6
68.3
CRITIC
Normalized inference c...
2026.04
74
68.7
S^2R
Normalized inference c...
2026.04
73.4
68.7
SC(k=5)
Normalized inference c...
2026.04
72
62.4
Self-Refine
Normalized inference c...
2026.04
68.6
59
CoT
Normalized inference c...
2026.04
68.4
60.3
Direct
Normalized inference c...
2026.04
62.4
52.3
Feedback
Search any
task
Search any
task