WizardLM-30B-fp16: benchmark results
TheBloke's Hugging Face publication of WizardLM's WizardLM 30B v1.0, whose original release is WizardLM/WizardLM-30B-V1.0. Conversion publication is credited separately from the original model creator. Provider: TheBloke. Access: Open.
Aggregate Rating 1367 ± 15, rank #7236 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Econometrics | 39.47 | Accuracy (%) | 91.5 |
| MMLU-by-task - Anatomy | 54.81 | Accuracy (%) | 90.7 |
| MMLU-by-task - Business Ethics | 63 | Accuracy (%) | 90.7 |
| MMLU-by-task - Professional Medicine | 60.29 | Accuracy (%) | 90.5 |
| MMLU-by-task - Marketing | 86.32 | Accuracy (%) | 90.3 |
| MMLU-by-task - Logical Fallacies | 73.62 | Accuracy (%) | 90.1 |
| MMLU-by-task - Professional Psychology | 64.38 | Accuracy (%) | 89.8 |
| MMLU-by-task - College Biology | 66.67 | Accuracy (%) | 89.5 |
| MMLU-by-task - Nutrition | 65.69 | Accuracy (%) | 89.3 |
| MMLU-by-task - Elementary Mathematics | 37.83 | Accuracy (%) | 89.1 |
| MMLU-by-task - Astronomy | 64.47 | Accuracy (%) | 88.9 |
| MMLU-by-task - High School Geography | 77.27 | Accuracy (%) | 88.9 |
Interactive version: theaggregate.ai/model?slug=wizardlm-30b-fp16 · How It Works · Data refreshed daily, snapshot 2026-11-08.