Puma-3B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1154 ± 16, rank #9908 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 - High School Physics | 31.79 | Accuracy (%) | 61.3 |
| MMLU-by-task - College Physics | 26.47 | Accuracy (%) | 57.9 |
| MMLU-by-task - Elementary Mathematics | 27.78 | Accuracy (%) | 45.3 |
| MMLU-by-task - Moral Scenarios | 24.69 | Accuracy (%) | 38.9 |
| MMLU-by-task - HellaSwag | 54.07 | Accuracy (%) | 37.7 |
| MMLU-by-task - Human Aging | 40.36 | Accuracy (%) | 36.9 |
| MMLU-by-task - Conceptual Physics | 33.62 | Accuracy (%) | 35.8 |
| MMLU-by-task - Business Ethics | 36 | Accuracy (%) | 35.2 |
| MMLU-by-task - Security Studies | 36.73 | Accuracy (%) | 34.6 |
| MMLU-by-task - High School European History | 30.3 | Accuracy (%) | 33.6 |
| MMLU-by-task - US Foreign Policy | 37 | Accuracy (%) | 33.3 |
Interactive version: theaggregate.ai/model?slug=puma-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.