Wizard-Vicuna-30B-Uncensored: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1359 ± 15, rank #7465 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Mathematics | 39 | Accuracy (%) | 92.7 |
| MMLU-by-task - Machine Learning | 48.21 | Accuracy (%) | 92.2 |
| MMLU-by-task - Virology | 51.81 | Accuracy (%) | 91.4 |
| MMLU-by-task - Management | 78.64 | Accuracy (%) | 89.7 |
| MMLU-by-task - Philosophy | 68.81 | Accuracy (%) | 89.2 |
| MMLU-by-task - Anatomy | 53.33 | Accuracy (%) | 88.9 |
| MMLU-by-task - Global Facts | 40 | Accuracy (%) | 88.7 |
| MMLU-by-task - High School Geography | 76.26 | Accuracy (%) | 87.9 |
| MMLU-by-task - ARC Challenge | 59.9 | Accuracy (%) | 87.8 |
| MMLU-by-task - Business Ethics | 60 | Accuracy (%) | 87.8 |
| MMLU-by-task - Professional Law | 45.76 | Accuracy (%) | 87.8 |
| MMLU-by-task - Marketing | 85.04 | Accuracy (%) | 87.7 |
Interactive version: theaggregate.ai/model?slug=wizard-vicuna-30b-uncensored · How It Works · Data refreshed daily, snapshot 2026-11-08.