AutoArena is an open-source tool for automated evaluations using LLM judges to rank GenAI systems.
AutoArenaの使い方?
Use AutoArena by installing it locally and inputting user prompts to evaluate generative AI systems.
AutoArenaの使用例
AutoArenaの主な機能
Automated head-to-head evaluations using LLM judges
Fine-tune custom judges
Generate leaderboards with Elo scores
Support for multiple judge models
Collaborate on evaluations in the cloud
AutoArenaのよくある質問
Is AutoArena free to use?
Can I run AutoArena locally?
What types of models can I use with AutoArena?
