Skip to main content
Paperai-evaluationv1.0

Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* Quality

by LMSYS / UC Berkeley / CMU / UCSD · open-source · Last verified 2026-03-17

Presents Vicuna-13B, an open-source chatbot created by fine-tuning LLaMA on ShareGPT conversation data, achieving approximately 90% of ChatGPT and Bard quality as judged by GPT-4. The paper introduces GPT-4 as an automated judge for chatbot evaluation, establishing a widely adopted evaluation paradigm for conversational AI.

https://lmsys.org/blog/2023-03-30-vicuna/
B
BAbove Average
Adoption: AQuality: AFreshness: BCitations: AEngagement: F

Specifications

License
Llama-derived non-commercial
Pricing
open-source
Capabilities
conversational-ai, gpt-4-evaluation, open-source-chat, instruction-following
Integrations
Use Cases
chatbot-development, model-evaluation, open-source-alternatives, research
API Available
No
Tags
evaluation, open-source, chatbot, vicuna, fine-tuning, gpt-4
Added
2026-03-17
Completeness
100%

Index Score

68.9
Adoption
80
Quality
82
Freshness
60
Citations
82
Engagement
0

Put AI to work for your business

Deploy this paper alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.

Explore the full AI ecosystem on Agents as a Service