pygmalion-7B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1215 ± 15, rank #9517 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Mathematics | 33 | Accuracy (%) | 61.7 |
| MMLU-by-task - HellaSwag | 57.61 | Accuracy (%) | 45.2 |
| MMLU-by-task - ARC Challenge | 47.95 | Accuracy (%) | 44.5 |
| MMLU-by-task - Conceptual Physics | 37.87 | Accuracy (%) | 44.3 |
| MMLU-by-task - Global Facts | 32 | Accuracy (%) | 44.3 |
| MMLU-by-task - Business Ethics | 44 | Accuracy (%) | 43.1 |
| MMLU-by-task - Professional Medicine | 44.49 | Accuracy (%) | 42.8 |
| MMLU-by-task - Public Relations | 49.09 | Accuracy (%) | 42.7 |
| MMLU-by-task - Anatomy | 41.48 | Accuracy (%) | 42.1 |
| MMLU-by-task - High School European History | 44.85 | Accuracy (%) | 40.5 |
| MMLU-by-task - Nutrition | 39.87 | Accuracy (%) | 40.1 |
| MMLU-by-task - International Law | 52.89 | Accuracy (%) | 40 |
Interactive version: theaggregate.ai/model?slug=pygmalion-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.