betagouv/ComparIA
Open source LLM arena created by the French Government
Collects human preference votes on LLM outputs across languages and sectors through blind pairwise comparisons, generating instruction and preference datasets published on Hugging Face. Built on a configurable, self-hostable architecture migrating from Gradio to FastAPI, with pluggable model support, customizable anonymization pipelines, and leaderboard generation. Integrates with EcoLogits for environmental impact tracking and targets multi-language expansion (French, Danish, Swedish, Estonian, Lithuanian) while enabling sector-specific and organizational deployments.
Stars
63
Forks
13
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/betagouv/ComparIA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
Skytliang/Multi-Agents-Debate
MAD: The first work to explore Multi-Agent Debate with Large Language Models :D
liuxiaotong/ai-dataset-radar
Multi-source async competitive intelligence engine for AI training data ecosystems with...
llm-ring/lmring
Open-source, self-hostable LLM arena with model compare, voting, and leaderboards
Arnoldlarry15/ARES-Dashboard
AI Red Team Operations Console
khoren93/ai-debates
Orchestrate epic battles between 600+ AI models (GPT-5, Gemini 3, DeepSeek R1). Real-time...