Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-hop Question Answering on LV-Eval (test)
Loading...
12.9
F1 Score
HippoRAG2
0.524
3.737
6.95
10.163
Feb 24, 2026
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
HippoRAG2
Backbone=Llama-3.3-70B...
2026.02
12.9
HELP
Backbone=Llama-3.3-70B...
2026.02
12.5
GraphRAG
Backbone=Llama-3.3-70B...
2026.02
11.2
LinearRAG
Backbone=Llama-3.3-70B...
2026.02
10.3
GritLM-7B
Backbone=Llama-3.3-70B...
2026.02
9.8
NV-Embed-v2
Backbone=Llama-3.3-70B...
2026.02
9.8
HippoRAG
Backbone=Llama-3.3-70B...
2026.02
8.4
Contriever
Backbone=Llama-3.3-70B...
2026.02
8.1
GTR
Backbone=Llama-3.3-70B...
2026.02
7.1
GTE-Qwen2-7B
Backbone=Llama-3.3-70B...
2026.02
7.1
None
Backbone=Llama-3.3-70B...
2026.02
6
BM25
Backbone=Llama-3.3-70B...
2026.02
5.9
RAPTOR
Backbone=Llama-3.3-70B...
2026.02
5
LightRAG
Backbone=Llama-3.3-70B...
2026.02
1
Feedback
Search any
task
Search any
task