Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-hop Question Answering on 2WikiMultihopQA OOD (Exact Match)
Loading...
39.2
Exact Match Accuracy
RECON
9.976
17.563
25.15
32.737
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
39.2
Search-R1
Backbone=Qwen2.5-7B-Ba...
2025.10
38.2
RECON
Backbone=Qwen2.5-3B-Ba...
2025.10
31.9
Rejection Sampling
2025.10
29.6
R1-instruct
2025.10
29.2
RECON
Backbone=Qwen2.5-7B-Ba...
2025.10
28.6
R1-base
2025.10
27.3
Search-R1
Backbone=Qwen2.5-3B-Ba...
2025.10
27.3
SFT
2025.10
25.9
Direct Inference
2025.10
25
RAG
2025.10
23.5
RECON
Backbone=Qwen2.5-3B-Ba...
2025.10
23
Search-o1
2025.10
17.6
IRCoT
2025.10
14.9
CoT
2025.10
11.1
Feedback
Search any
task
Search any
task