Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Hop Reasoning on MuSiQue (Accuracy and Recall)
Loading...
36.67
Accuracy
HyGRAG
6.9884
14.6942
22.4
30.1058
Jun 16, 2026
Accuracy
Recall
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Recall
HyGRAG
Base LLM=Qwen3-8B
2026.06
36.67
49.33
L-LightRAG
Base LLM=Qwen3-8B
2026.06
33.1
47.52
HippoRAG2
Base LLM=Qwen3-8B
2026.06
25.87
37.08
HippoRAG
Base LLM=Qwen3-8B
2026.06
24.9
38.88
RAPTOR
Base LLM=Qwen3-8B
2026.06
23.67
35.37
VanillaRAG
Base LLM=Qwen3-8B
2026.06
23.6
35.26
L-GraphRAG
Base LLM=Qwen3-8B
2026.06
18.53
32.79
CoT
Base LLM=Qwen3-8B
2026.06
10.5
27.97
Zero-shot
Base LLM=Qwen3-8B
2026.06
8.13
22.38
Feedback
Search any
task
Search any
task