Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Single-hop QA on NQ (test)
Loading...
42
Token-level F1
RAG-Critic
18.912
24.906
30.9
36.894
Apr 16, 2026
Token-level F1
Updated 14d ago
Evaluation Results
Method
Method
Links
Token-level F1
RAG-Critic
Type=Agentic RAG
2026.04
42
RePAIR
Training Phase=full
2026.04
40.3
MetaRAG
Type=Agentic RAG
2026.04
40.2
RePAIR (online)
Training Phase=online
2026.04
38.8
RePAIR (offline)
Training Phase=offline
2026.04
38.4
Standard RAG
Type=Standard RAG
2026.04
38.3
Self-RAG
Type=Agentic RAG
2026.04
32.3
Self-Refine
Type=Agentic RAG
2026.04
22.3
FLARE
Type=Agentic RAG
2026.04
19.8
Feedback
Search any
task
Search any
task