Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Retrieval-Augmented Question Answering on MultiHop-RAG
Loading...
69.2
Correctness (%)
Monolithic
28.224
38.862
49.5
60.138
Jun 9, 2026
Correctness (%)
Faithfulness
Latency (p50, s)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Correctness (%)
Faithfulness
Latency (p50, s)
Monolithic
Base Model=Qwen-2.5-7B
2026.06
69.2
46
2.1
MASDR-RAG
Base Model=Qwen-2.5-7B
2026.06
61.6
43
4.4
HYBRID-ROUTED
Base Model=Qwen-2.5-7B
2026.06
61
48
3.1
Regex-Scoped
Base Model=Qwen-2.5-7B
2026.06
58
47
2.3
SCOUT-RAG
Base Model=Qwen-2.5-7B
2026.06
55.2
-
21
MA-RAG
Base Model=Qwen-2.5-7B
2026.06
29.8
-
15.6
Feedback
Search any
task
Search any
task