Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Context Compression & QA on NQ (val)
Loading...
35.8
EM
FTHSS
13.648
19.399
25.15
30.901
Feb 16, 2025
EM
F1
Updated 4d ago
Evaluation Results
Method
Method
Links
EM
F1
FTHSS
Category=Streamlining,...
2025.02
35.8
45.6
Compress&QA
Category=Chain of Mode...
2025.02
35
48.3
Prompt Tuning
Category=Single Model,...
2025.02
32.7
45.1
Standard RAG
Category=Single Model,...
2025.02
28.5
44.8
Distill
Category=Streamlining,...
2025.02
21.4
33.1
Native
Category=Single Model,...
2025.02
14.5
26.4
Feedback
Search any
task
Search any
task