pygmalion-instruct: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1221 ± 16, rank #9473 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 34 | Accuracy (%) | 82 |
| MMLU-by-task - Global Facts | 37 | Accuracy (%) | 76.3 |
| MMLU-by-task - ARC Challenge | 50.51 | Accuracy (%) | 53.5 |
| MMLU-by-task - TruthfulQA MC1 | 28.64 | Accuracy (%) | 51.5 |
| MMLU-by-task - HellaSwag | 58.46 | Accuracy (%) | 48.4 |
| MMLU-by-task - College Mathematics | 31 | Accuracy (%) | 45.5 |
| MMLU-by-task - Clinical Knowledge | 44.53 | Accuracy (%) | 43.2 |
| MMLU-by-task - Logical Fallacies | 41.72 | Accuracy (%) | 41.1 |
| MMLU-by-task - International Law | 54.55 | Accuracy (%) | 40.6 |
| MMLU-by-task - Virology | 36.75 | Accuracy (%) | 40.4 |
| MMLU-by-task - Anatomy | 40 | Accuracy (%) | 40.2 |
| MMLU-by-task - Moral Disputes | 40.75 | Accuracy (%) | 39.4 |
Interactive version: theaggregate.ai/model?slug=pygmalion-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.