Your key is stored only in your browser and is never sent anywhere except directly to OpenAI's API.
Need a key? Get one at platform.openai.com. Judging uses GPT-5.4 Mini. Every model and judge call is billed to your OpenAI account at OpenAI’s rates. Save an empty field to remove a saved key.
Litmiq prompt evaluator — compare OpenAI models side by side
Models to Test
Test Cases
No evals yet
Configure your system prompt, choose models, add test cases, and hit Run Evals. Results appear here with per-metric scores.