wizard-mega-13B-GPTQ: benchmark results
TheBloke's GPTQ publication of Wizard Mega 13B, whose original release is openaccess-ai-collective/wizard-mega-13b. Conversion publication is credited separately from the original model creator. Quantization method does not establish a single effective bit width or exact evaluated branch for this catalog row. Provider: TheBloke. Access: Open.
Aggregate Rating 1133 ± 16, rank #10271 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC2 | 48.69 | Accuracy (%) | 69.4 |
| MMLU-by-task - Moral Scenarios | 26.26 | Accuracy (%) | 53.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 48.69 | MC2 (%) (0-shot) | 42.2 |
| Open LLM Leaderboard v1 - WinoGrande | 74.74 | Accuracy (%) (5-shot) | 38.5 |
| MMLU-by-task - Electrical Engineering | 31.72 | Accuracy (%) | 35.4 |
| MMLU-by-task - High School Statistics | 31.48 | Accuracy (%) | 34.8 |
| MMLU-by-task - College Physics | 22.55 | Accuracy (%) | 34.3 |
| MMLU-by-task - College Chemistry | 26 | Accuracy (%) | 29.9 |
| MMLU-by-task - High School Computer Science | 31 | Accuracy (%) | 29.4 |
| Open LLM Leaderboard v1 - GSM8K | 8.95 | Accuracy (%) (5-shot) | 29.3 |
| MMLU-by-task - Formal Logic | 25.4 | Accuracy (%) | 28.9 |
| MMLU-by-task - TruthfulQA MC1 | 24.6 | Accuracy (%) | 28.9 |
Interactive version: theaggregate.ai/model?slug=wizard-mega-13b-gptq · How It Works · Data refreshed daily, snapshot 2026-11-08.