Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on 2WikiMultiHopQA 1,000 questions sample (val)
Loading...
71.2
Containment Accuracy
FlowRAG
30.016
40.708
51.4
62.092
Jun 16, 2026
Containment Accuracy
GPT Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Containment Accuracy
GPT Accuracy
FlowRAG
LLM=GPT-4o-mini, k=5
2026.06
71.2
65.2
LinearRAG
LLM=GPT-4o-mini, k=5
2026.06
68.9
62.7
GFM-RAG
LLM=GPT-4o-mini, k=5
2026.06
66.8
59.6
HippoRAG
LLM=GPT-4o-mini, k=5
2026.06
66.1
59.9
HippoRAG2
LLM=GPT-4o-mini, k=5
2026.06
62.7
55
LightRAG
LLM=GPT-4o-mini, k=5
2026.06
55.2
39
E2GraphRAG
LLM=GPT-4o-mini, k=5
2026.06
54.3
38.1
RAPTOR
LLM=GPT-4o-mini, k=5
2026.06
50.1
42.1
Vanilla RAG
LLM=GPT-4o-mini, k=5
2026.06
48.6
43
G-retriever
LLM=GPT-4o-mini, k=5
2026.06
46.6
27.1
KGP
LLM=GPT-4o-mini, k=5
2026.06
31.6
30
Feedback
Search any
task
Search any
task