wizardLM-13B-1.0-fp16: benchmark results
TheBloke's Hugging Face publication of WizardLM 13B 1.0, whose original release is victor123/WizardLM-13B-1.0. Conversion publication is credited separately from the original model creator. Provider: TheBloke. Access: Open.
Aggregate Rating 1327 ± 15, rank #8226 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Formal Logic | 39.68 | Accuracy (%) | 85.5 |
| MMLU-by-task - Management | 75.73 | Accuracy (%) | 84.7 |
| MMLU-by-task - TruthfulQA MC1 | 35.62 | Accuracy (%) | 83.7 |
| MMLU-by-task - Professional Medicine | 55.51 | Accuracy (%) | 80.4 |
| MMLU-by-task - Security Studies | 64.08 | Accuracy (%) | 80.3 |
| MMLU-by-task - High School Physics | 34.44 | Accuracy (%) | 78.7 |
| MMLU-by-task - TruthfulQA MC2 | 50.55 | Accuracy (%) | 78.6 |
| MMLU-by-task - Medical Genetics | 60 | Accuracy (%) | 78.5 |
| MMLU-by-task - Sociology | 74.13 | Accuracy (%) | 78.2 |
| MMLU-by-task - Human Sexuality | 63.36 | Accuracy (%) | 76.4 |
| MMLU-by-task - Global Facts | 37 | Accuracy (%) | 76.3 |
| MMLU-by-task - Professional Law | 42.24 | Accuracy (%) | 76 |
Interactive version: theaggregate.ai/model?slug=wizardlm-13b-1-0-fp16 · How It Works · Data refreshed daily, snapshot 2026-11-08.