... everyone! 7 months ago I launched PromptPerf on Product Hunt and got feedback that changed everything: - "Sadly no Gemini" Now there's 100+ models - "API key friction" Now works without signup - "Need multi-model comparison" Now compare 5 models side-by-side Today we're back with 2.0 and I built exactly what the community asked for. What it does: You enter your actual prompt + what a good answer looks like, pick models (GPT-4o, Claude, Gemini, Llama ...

... building on sand. I got tired of playing prompt roulette. Tired of: Copy-pasting prompts into playgrounds Switching models manually Changing temperature settings Scoring responses by eye Losing track of what worked and what didn t So I built PromptPerf A fast, focused prompt testing playground built for serious AI builders. Run your prompt across GPT-4o, GPT-4, GPT-3.5 Test across temperatures Check consistency over multiple runs Compare model outputs to your ideal result No more guessing ... ... more hope-it-works. Just real validation. Because vague outputs break trust. And in AI trust is your product . PromptPerf

... completed my proof-of-concept for the AI evaluation tool - successfully testing prompts across configs (Models x Temps x Runs). https://promptperf.dev/ Hi, I am building a AI Model Prompt Optimising tool that will run through multiple AI models across various temperature settings for X number of runs. This saves time doing multiple tests, example user wants to test 3 questions/prompts for an expected answer across 4 models and the test would include 3 temperature options, each test ... ... Select Models Choose which AI models you want to evaluate from our supported options like GPT-4o, Claude, Gemini, and more. 4. Configure Settings Set the temperature values and number of runs for each configuration to test various creativity vs