Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-hop Retrieval on Average (MuSiQue, 2Wiki, HotpotQA)
Loading...
72.5
R@2
GFM-RAG
35.06
44.78
54.5
64.22
Mar 16, 2026
R@2
R@5
Updated 1mo ago
Evaluation Results
Method
Method
Links
R@2
R@5
GFM-RAG
LLM=GPT-4o-mini
2026.03
72.5
80.5
C2RAG
LLM=GPT-4o-mini
2026.03
69.3
82.1
NeuroPath
LLM=GPT-4o-mini
2026.03
67.1
81.3
Iter-RetGen
LLM=GPT-4o-mini
2026.03
62.3
75.5
HippoRAG
LLM=GPT-4o-mini
2026.03
58.4
73.9
HippoRAG2
LLM=GPT-4o-mini
2026.03
56.4
71.2
IRCoT
LLM=GPT-4o-mini
2026.03
55.3
69.5
G-retriever
LLM=GPT-4o-mini
2026.03
49.7
57.6
BM25
LLM=GPT-4o-mini
2026.03
46.6
58.2
LightRAG
LLM=GPT-4o-mini
2026.03
36.5
49.3
Feedback
Search any
task
Search any
task