manticore-13B-chat-pyg-GPTQ: benchmark results
TheBloke's GPTQ publication of Manticore 13B Chat Pyg, whose original release is openaccess-ai-collective/manticore-13b-chat-pyg. 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 1299 ± 16, rank #8751 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Mathematics | 37 | Accuracy (%) | 85.2 |
| MMLU-by-task - Abstract Algebra | 34 | Accuracy (%) | 82 |
| MMLU-by-task - Professional Accounting | 40.78 | Accuracy (%) | 72 |
| MMLU-by-task - College Physics | 29.41 | Accuracy (%) | 71.1 |
| MMLU-by-task - ARC Challenge | 55.12 | Accuracy (%) | 69.8 |
| MMLU-by-task - TruthfulQA MC1 | 32.68 | Accuracy (%) | 69.3 |
| MMLU-by-task - High School Computer Science | 54 | Accuracy (%) | 67.7 |
| MMLU-by-task - Anatomy | 48.15 | Accuracy (%) | 66.5 |
| MMLU-by-task - US Foreign Policy | 77 | Accuracy (%) | 65.8 |
| MMLU-by-task - Professional Law | 39.7 | Accuracy (%) | 64.6 |
| MMLU-by-task - Machine Learning | 35.71 | Accuracy (%) | 64.2 |
| MMLU-by-task - Astronomy | 50.66 | Accuracy (%) | 63.8 |
Interactive version: theaggregate.ai/model?slug=manticore-13b-chat-pyg-gptq · How It Works · Data refreshed daily, snapshot 2026-11-08.