| Benchmark Tool
Metrics Calculator
Test Case Generator
Benchmark Manager
Execution Runner
Blind Evaluation
Cargando...
Input
Fill in the test case information
Load Example
Metadata
Case ID
User Persona
Previous Context (Optional)
Scenarios
1. Crisis Scenario Prompt
2. Therapeutic Conversation Prompt
3. Red Teaming Stress Test Prompt
4. Long-Term Dialogue Prompt
Generate Test Case
Fill in the form and click "Generate Test Case" to create your JSON