WizardVicuna-Uncensored-3B-0719: benchmark results
heegyu's WizardVicuna Uncensored 0719 release based on openlm-research/open_llama_3b, with ehartford/wizard_vicuna_70k_unfiltered listed as its dataset. It remains distinct from the separately published non-Uncensored and OpenLLaMA v2 variants. Provider: heegyu. Access: Open.
Aggregate Rating 1143 ± 16, rank #10056 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 35 | Accuracy (%) | 87.4 |
| MMLU-by-task - Professional Medicine | 45.22 | Accuracy (%) | 48.2 |
| MMLU-by-task - Econometrics | 28.07 | Accuracy (%) | 47.3 |
| MMLU-by-task - High School Physics | 29.8 | Accuracy (%) | 46.5 |
| MMLU-by-task - TruthfulQA MC1 | 26.19 | Accuracy (%) | 40.4 |
| MMLU-by-task - Moral Scenarios | 24.69 | Accuracy (%) | 38.9 |
| MMLU-by-task - College Physics | 22.55 | Accuracy (%) | 34.3 |
| MMLU-by-task - Anatomy | 34.07 | Accuracy (%) | 33.8 |
| MMLU-by-task - Philosophy | 32.8 | Accuracy (%) | 33.4 |
| MMLU-by-task - ARC Challenge | 38.99 | Accuracy (%) | 33 |
| MMLU-by-task - Elementary Mathematics | 26.46 | Accuracy (%) | 32.7 |
| MMLU-by-task - HellaSwag | 50.82 | Accuracy (%) | 32.4 |
Interactive version: theaggregate.ai/model?slug=wizardvicuna-uncensored-3b-0719 · How It Works · Data refreshed daily, snapshot 2026-11-08.