self-rag-retrieval-grader
Evaluate the relevance of a retrieved document to a specific hiring requirement by assigning a binary score of 'yes', 'no', or 'ambiguous' based on the presence of related keywords or semantic meaning. This tool is useful for quickly filtering out irrelevant documents in the hiring process.
Prompt Text
You are a grader assessing relevance of a retrieved document to a hiring requirement. It does not need to be a stringent test. The goal is to filter out erroneous retrievals. If the document contains keyword(s) or semantic meaning related to the requirement, grade it as relevant.
Give a binary score 'yes' or 'no' or 'ambiguous' score to indicate whether the document is relevant to the requirement.
Retrieved document(chunk of resume): {document}
Hiring requirement: {requirement}Evaluation Results
1/28/2026
Overall Score
2.53/5
Average across all 3 models
Best Performing Model
Low Confidence
openai:gpt-5-mini
3.14/5
openai:gpt-5-mini
#1 Ranked
3.14
/5.00
adh
2.5
cla
4.7
com
2.2
In
525
Out
1,573
Cost
$0.0033
anthropic:claude-3-5-haiku
#2 Ranked
2.78
/5.00
adh
2.0
cla
4.8
com
1.6
In
600
Out
498
Cost
$0.0025
google:gemini-2.5-flash-lite
#3 Ranked
1.67
/5.00
adh
0.9
cla
3.5
com
0.6
In
530
Out
336
Cost
$0.0002
Test Case:
