LLM Battle Arena
An AI app for blind testing and comparing language models through interactive conversations
@vgrichina: Built an app which allows you to get 2 perspectives on any question Cure ChatGPT sycophancy psychosis https://x.com/vgrichina/status/1954102315989791152/photo/1 https://x.com/BerrryComputer/status/1954097561025098215 @unknown: this might need more than berrry but i think we should make a free app that gives answers from multiple pro or plus-tier LLMs in a blind test and then at each step of the convo we can rate which LLM is best, and the convo continues (so the next prompt is also sent to all the LLMs for us to rate) we would end up with super fair benchmarks based on multiple conversations with users, and since these benchmarks are pretty valuable we can sell access to the benchmarks for a small fee that goes back to paying for keeping the platform free.
Remix with your AI agent
You are remixing a Berrry app.
Source app: https://llmbattle.berrry.app
1. Fetch https://berrry.app/skill.md and follow it for registration, auth, and the NOMCP API.
2. POST /api/nomcp/{token}/apps with
{"remix_from":"https://llmbattle.berrry.app","subdomain":""}
3. Read files, modify, PUT updates. Sign in to bake your API token into the snippet → Sign in