vicuna-33B: benchmark results
Provider: LMSYS. Access: Open.
Aggregate Rating 1412 ± 46, rank #5525 of 10916 rated models, from 27 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MoralChoice | 98.5 | MoralChoice Acc (%) | 50 |
| Chatbot Arena (Text - Creative Writing) | 1172 | Arena Score | 17 |
| Chatbot Arena (Text - Entertainment, Sports & Media) | 1166 | Arena Score | 16.2 |
| Chatbot Arena (Text - Writing, Literature & Language) | 1171 | Arena Score | 15.2 |
| Chatbot Arena (Text - Life, Physical & Social Science) | 1192 | Arena Score | 13.3 |
| Chatbot Arena (Text - Multi-Turn) | 1141 | Arena Score | 12.9 |
| Chatbot Arena (Text - Software & IT Services) | 1189 | Arena Score | 12.6 |
| Chatbot Arena (Text) | 1173 | Elo | 12.6 |
| Chatbot Arena (Text - Non-English) | 1122 | Arena Score | 12.5 |
| Chatbot Arena (Text - Instruction Following) | 1140 | Arena Score | 11.6 |
| Chatbot Arena (Text - English) | 1200 | Arena Score | 11.4 |
| Chatbot Arena (Text - Hard Prompts) | 1165 | Arena Score | 10.9 |
Interactive version: theaggregate.ai/model?slug=vicuna-33b · How It Works · Data refreshed daily, snapshot 2026-11-08.