đ Model Evaluation
Disconnected
â Back to Chat
âšī¸ Uses Amazon Bedrock Model Evaluation with LLM-as-a-Judge (Claude Opus 4.5). Metrics: Correctness, Completeness, Coherence, Relevance, Helpfulness.
Test Cases
#
Category
Prompt
Reference Response
Connecting...
Run Evaluation (All Models)
Check Status
Results
Comparison