WizardLM-70B-V1.0: benchmark results
Microsoft/WizardLM Team's WizardLM-70B-V1.0, a Llama-2-70B-based model in the WizardLM family built to align large pretrained language models with complex instruction-following capability. Provider: Microsoft. Released 2023-08-09. Access: Open.
Aggregate Rating 1396 ± 13, rank #1224 of 1640 rated models, from 145 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Public Relations | 72.73 | Accuracy (%) | 95.9 |
| MMLU-by-task - High School Physics | 44.37 | Accuracy (%) | 95.5 |
| MMLU-by-task - Formal Logic | 46.83 | Accuracy (%) | 95.4 |
| MMLU-by-task - Global Facts | 46 | Accuracy (%) | 94.9 |
| MMLU-by-task - Management | 81.55 | Accuracy (%) | 94.1 |
| MMLU-by-task - High School European History | 81.82 | Accuracy (%) | 93.8 |
| MMLU-by-task - Machine Learning | 49.11 | Accuracy (%) | 93.5 |
| MMLU-by-task - Professional Accounting | 51.77 | Accuracy (%) | 93.5 |
| MMLU-by-task - College Biology | 77.08 | Accuracy (%) | 93.4 |
| MMLU-by-task - High School Microeconomics | 71.01 | Accuracy (%) | 93.1 |
| MMLU-by-task - Miscellaneous | 82.76 | Accuracy (%) | 93.1 |
| MMLU-by-task - TruthfulQA MC1 | 38.56 | Accuracy (%) | 93.1 |
Interactive version: theaggregate.ai/model?slug=wizardlm-70b-v1-0 · How It Works · Data refreshed daily, snapshot 2026-10-13.