Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on WYDOT 200-q
Loading...
35.1
Correlation (%)
Regex-Scoped
10.036
16.543
23.05
29.557
Jun 9, 2026
Correlation (%)
Faithfulness
API Calls
Updated 1mo ago
Evaluation Results
Method
Method
Links
Correlation (%)
Faithfulness
API Calls
Regex-Scoped
Backbone=Qwen-2.5-7B,...
2026.06
35.1
61
1
Monolithic
Backbone=Qwen-2.5-7B,...
2026.06
33.5
61
1
HYBRID-ROUTED
Backbone=Qwen-2.5-7B,...
2026.06
30.3
43
1.5
MASDR-RAG
Backbone=Qwen-2.5-7B,...
2026.06
28.7
48
2.1
ReAct
Backbone=Qwen-2.5-7B,...
2026.06
24.5
59
2.3
SCOUT-RAG
Backbone=Qwen-2.5-7B,...
2026.06
24.1
-
10.4
MA-RAG
Backbone=Qwen-2.5-7B,...
2026.06
11
-
22.3
Feedback
Search any
task
Search any
task