wizardLM-7B-HF: benchmark results
TheBloke's full merged-weight Hugging Face publication reconstructed from victor123/WizardLM and the corresponding original Llama weights. The original delta release remains separately credited; this repository distributes the merged model rather than only delta weights. Provider: TheBloke. Access: Open.
Aggregate Rating 1228 ± 17, rank #9435 of 10916 rated models, from 67 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 35 | Accuracy (%) | 87.4 |
| MMLU-by-task - TruthfulQA MC1 | 31.46 | Accuracy (%) | 64.5 |
| MMLU-by-task - Elementary Mathematics | 30.69 | Accuracy (%) | 60.4 |
| MMLU-by-task - TruthfulQA MC2 | 45.58 | Accuracy (%) | 54 |
| MMLU-by-task - Conceptual Physics | 40 | Accuracy (%) | 52.7 |
| MMLU-by-task - Business Ethics | 48 | Accuracy (%) | 52.2 |
| MMLU-by-task - Anatomy | 43.7 | Accuracy (%) | 47.1 |
| MMLU-by-task - Human Aging | 51.12 | Accuracy (%) | 45.5 |
| MMLU-by-task - ARC Challenge | 48.46 | Accuracy (%) | 45.4 |
| MMLU-by-task - Virology | 39.16 | Accuracy (%) | 44.9 |
| MMLU-by-task - Global Facts | 32 | Accuracy (%) | 44.3 |
| MMLU-by-task - Astronomy | 40.13 | Accuracy (%) | 44 |
Interactive version: theaggregate.ai/model?slug=wizardlm-7b-hf · How It Works · Data refreshed daily, snapshot 2026-11-08.