Project-Baize-v2-7B-GPTQ: benchmark results
TheBloke's GPTQ publication of Project Baize V2 7B, whose original release is project-baize/baize-v2-7b. 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 1216 ± 15, rank #9506 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Physics | 28.43 | Accuracy (%) | 67.4 |
| MMLU-by-task - High School Mathematics | 27.41 | Accuracy (%) | 54.7 |
| MMLU-by-task - College Computer Science | 40 | Accuracy (%) | 54.4 |
| MMLU-by-task - Formal Logic | 30.95 | Accuracy (%) | 52.2 |
| MMLU-by-task - Professional Medicine | 45.22 | Accuracy (%) | 48.2 |
| MMLU-by-task - Moral Scenarios | 25.25 | Accuracy (%) | 46.6 |
| MMLU-by-task - High School Physics | 29.8 | Accuracy (%) | 46.5 |
| MMLU-by-task - College Mathematics | 31 | Accuracy (%) | 45.5 |
| MMLU-by-task - Medical Genetics | 45 | Accuracy (%) | 41.9 |
| MMLU-by-task - HellaSwag | 55.79 | Accuracy (%) | 41.3 |
| MMLU-by-task - High School World History | 49.37 | Accuracy (%) | 41.2 |
| MMLU-by-task - Human Sexuality | 41.98 | Accuracy (%) | 40.8 |
Interactive version: theaggregate.ai/model?slug=project-baize-v2-7b-gptq · How It Works · Data refreshed daily, snapshot 2026-11-08.