Find out which AI answers your prompt best, and whether your changes made it better or worse.
Type the instructions you give an AI. This app sends them to several AIs at once, has another AI grade every answer from 1 to 10, and shows you which one is the most accurate, the fastest and the cheapest.
The problem it solves
If you use AI in a product, a business or a school project, you keep tweaking your prompt. Without testing, you're guessing.
"Is my new prompt actually better?"
You change a few words, check two answers, and they look fine. But did it quietly break ten others?
"Which AI should I pick?"
GPT, Gemini, Llama… they differ a lot in quality, speed and price, and the best one depends on your task.
"I can't read 100 answers by hand."
A grader AI scores every answer and explains why, so you only read the ones that matter.
Change your prompt, see exactly what changed
Save a set of test inputs once. Every time you edit your prompt and run it again, you get a clear before-and-after report like this:
Example only. You can open each changed answer and read it before and after, side by side.
Two ways to use it
Quick test
Best for: trying an idea. One prompt, one example. You see each AI's answer and grade in seconds. Nothing is saved.
Start a quick test →Evaluate many inputs
Best for: getting it right before you rely on it. Test 10 to 500 examples, get a report card per AI, and track changes over time.
Start an evaluation →Who it's for
Developers
Building a chatbot or AI feature, and wanting tests for prompts the way you have tests for code.
Product and support teams
Writing prompts for summaries, replies or classification, and needing proof they work before launch.
Students and learners
Learning prompt writing, and seeing how different AIs respond to the same instructions.
Words you'll see
- Prompt
- The instructions you give an AI, for example "Summarize this complaint in one sentence."
- Input
- The text the prompt works on, for example one customer email. Write {{input}} in your prompt to mark where it goes.
- Model
- A specific AI that answers your prompt, such as Gemini, GPT or Llama. Different models give different answers at different speeds and prices.
- Grader
- A second AI that reads each answer and scores it from 1 to 10, with a short reason. It saves you from reading every answer yourself.
- Ideal answer
- What a perfect answer looks like, if you know it. Giving one makes grading much more accurate.
- Pass mark
- The lowest score that counts as a good answer. It is 7 out of 10 by default.
Common questions
Do I need to know how to code?
No. If you can write instructions for an AI, you can use this. Type a prompt, pick some AIs, and press Run.
Is it free?
It can be. Free AI options (Google Gemini, Groq, OpenRouter's free models and Ollama on your own computer) are marked "free". Paid models show their price, and every result shows what it cost.
Which AI should I use?
That's exactly what this tool helps you decide. Run the same prompt on two or three models and compare the grades, speed and cost side by side.
Why should I test many inputs instead of one?
One good answer can be luck. Testing 10 to 30 realistic inputs shows how a prompt behaves in general, including the awkward cases.