Open-source self-hosted LLM comparison tool for your own prompt
Open-source self-hosted LLM comparison tool for your own prompt
Hi HN, I just pushed Duelr v0.1.1 to GitHub and would love your feedback. Each month a new model claims “30 % better,” yet I was still copy-pasting prompts into half a dozen playground tabs. Existing evaluation suites (Promptfoo, LangSmith, etc.) are great but heavy; I wanted a <1-minute CLI / local web tool. How it works - Paste a prompt (or JSON template) → click Compare All. - Duelr fires the same request to models you selected such as GPT-4o, Claude 4 Sonnet, Groq (more drivers coming). - It shows, side-by-side: - response text - end-to-end latency (ms) - token counts → cost spent for the request - simplicity and readability score (more heuristics will be coming) The goal is to see model's performance in your real prompt instead of generic academic benchmarks. Repo: https://github.com/stashlabs/duelr P.S.: First time I’ve ever open-sourced a full tool.
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Correct prediction on native model
Similar products
Europa – An Open Source Self-Hosted Container Registry
Europa – An Open Source Self Hosted Container Registry
Open-Source Price Comparison of Self-Hosted GPUs and LLM Providers
Open-source, Self-hosted, Dockerized Gumroad alternative
OneUptime – Self Hosted Open Source Datadog Alternative
Pivor, Open source self-hosted CRM
Forte, an open-source self-hosted music platform, is now federated
Volatile messaging (self hosted and open source)
Step-ca is a self-hosted open-source CA that supports ACME
Lightspeed – subsecond, open source, self hosted stream from OBS