Launching today
orbench
benchmark LLMs on your own tasks before you switch model
6 followers
benchmark LLMs on your own tasks before you switch model
6 followers
You can pick a model on a gut feeling, orbenchmark it. orbench is a desktop app that lets you benchmark LLMs on your own tasks, A public leaderboard ranks models on someone else's prompts. Production evals give you more insights, but only after you've done all the work to implement the new models. orbench is the step in between: bring your real tasks (csv or HF dataset), pick any models on OpenRouter, and your own rubric grade every answer with an AI judge, a blind human review, or both.
Payment Required
Launch Team
CloudflareYour next app belongs on Cloudflare Workers. Deploy for free
Promoted
When you need to know if a new LLM will actually save money without dropping quality on your own prompts, you have to test it yourself. orbench helps you run benchmarks on any OpenRouter model with your data, measures quality, latency and real cost, and produces a single report for the team that you can rerun every time a new model drops. Keen to hear your thoughts and how you/your team currently evaluate which model to implement in production!
Looks super useful especially when you are having to tell the CFO why it is important to switch or not switch! I look forward to getting the same for OCRs.
@igorcarron Thanks Igor for your support!!