WizardLM-13B-V1-1-SuperHOT-8K-fp16: benchmark results
TheBloke's Hugging Face publication of WizardLM's WizardLM 13B V1.1, whose original release is WizardLM/WizardLM-13B-V1.1. Conversion publication is credited separately from the original model creator. The card describes a SuperHOT merge with extended-context inference requirements; its extension is not treated as the original model’s native context. Provider: TheBloke. Access: Open.
Aggregate Rating 1307 ± 16, rank #8598 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC1 | 38.31 | Accuracy (%) | 92.6 |
| MMLU-by-task - TruthfulQA MC2 | 54.19 | Accuracy (%) | 91.7 |
| MMLU-by-task - Abstract Algebra | 34 | Accuracy (%) | 82 |
| MMLU-by-task - College Chemistry | 40 | Accuracy (%) | 73.8 |
| MMLU-by-task - Astronomy | 54.61 | Accuracy (%) | 73.5 |
| MMLU-by-task - ARC Challenge | 55.46 | Accuracy (%) | 71.5 |
| MMLU-by-task - High School Physics | 33.11 | Accuracy (%) | 70.8 |
| MMLU-by-task - Nutrition | 58.82 | Accuracy (%) | 69.8 |
| MMLU-by-task - Sociology | 70.65 | Accuracy (%) | 67.8 |
| MMLU-by-task - Management | 69.9 | Accuracy (%) | 67 |
| MMLU-by-task - Clinical Knowledge | 56.23 | Accuracy (%) | 66.5 |
| MMLU-by-task - Professional Law | 40.16 | Accuracy (%) | 66.4 |
Interactive version: theaggregate.ai/model?slug=wizardlm-13b-v1-1-superhot-8k-fp16 · How It Works · Data refreshed daily, snapshot 2026-11-08.