WizardLM-13B-Uncensored: benchmark results
Provider: Microsoft. Access: Open.
Aggregate Rating 1269 ± 15, rank #9076 of 10916 rated models, from 74 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Mathematics | 39 | Accuracy (%) | 92.7 |
| MMLU-by-task - Global Facts | 38 | Accuracy (%) | 81.7 |
| MMLU-by-task - Machine Learning | 40.18 | Accuracy (%) | 81.7 |
| MMLU-by-task - TruthfulQA MC1 | 31.7 | Accuracy (%) | 65.5 |
| InstructEval - Problem Solving | 36.5 | Average (%, MMLU/BBH/DROP/CRASS/HumanEval) | 65.3 |
| MMLU-by-task - Moral Scenarios | 28.49 | Accuracy (%) | 63.7 |
| MMLU-by-task - High School Mathematics | 28.15 | Accuracy (%) | 61.8 |
| MMLU-by-task - TruthfulQA MC2 | 46.73 | Accuracy (%) | 58.4 |
| MMLU-by-task - Conceptual Physics | 41.28 | Accuracy (%) | 58.2 |
| MMLU-by-task - College Computer Science | 41 | Accuracy (%) | 57.6 |
| MMLU-by-task - High School Computer Science | 48 | Accuracy (%) | 57.3 |
| MMLU-by-task - Public Relations | 56.36 | Accuracy (%) | 56.1 |
Interactive version: theaggregate.ai/model?slug=wizardlm-13b-uncensored · How It Works · Data refreshed daily, snapshot 2026-11-08.