Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-hop Question Answering on Bamboogle OOD
Loading...
44.6
Exact Match Accuracy
RECON
7.368
17.034
26.7
36.366
Oct 12, 2025
Exact Match Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match Accuracy
RECON
Backbone=Qwen2.5-7B-Ba...
2025.10
44.6
Search-R1
Backbone=Qwen2.5-7B-Ba...
2025.10
43.2
Rejection Sampling
2025.10
35.5
Search-o1
2025.10
29.6
R1-base
2025.10
29.6
R1-instruct
2025.10
29.3
CoT
2025.10
23.2
RECON
Backbone=Qwen2.5-3B-Ba...
2025.10
22.6
IRCoT
2025.10
22.4
RAG
2025.10
20.8
RECON
Backbone=Qwen2.5-7B-Ba...
2025.10
12.7
RECON
Backbone=Qwen2.5-3B-Ba...
2025.10
12.1
Direct Inference
2025.10
12
SFT
2025.10
11.2
Search-R1
Backbone=Qwen2.5-3B-Ba...
2025.10
8.8
Feedback
Search any
task
Search any
task