Griffin-3B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1148 ± 15, rank #10004 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Physics | 30.46 | Accuracy (%) | 50.8 |
| MMLU-by-task - Elementary Mathematics | 28.31 | Accuracy (%) | 47.9 |
| MMLU-by-task - Global Facts | 32 | Accuracy (%) | 44.3 |
| MMLU-by-task - High School Mathematics | 26.3 | Accuracy (%) | 40 |
| MMLU-by-task - College Mathematics | 30 | Accuracy (%) | 38.1 |
| MMLU-by-task - HellaSwag | 54.24 | Accuracy (%) | 38.1 |
| MMLU-by-task - Human Aging | 41.26 | Accuracy (%) | 37.9 |
| MMLU-by-task - Business Ethics | 37 | Accuracy (%) | 36 |
| MMLU-by-task - Conceptual Physics | 33.62 | Accuracy (%) | 35.8 |
| MMLU-by-task - Professional Accounting | 28.72 | Accuracy (%) | 35.6 |
| MMLU-by-task - Computer Security | 35 | Accuracy (%) | 32.3 |
| MMLU-by-task - High School World History | 29.96 | Accuracy (%) | 31.6 |
Interactive version: theaggregate.ai/model?slug=griffin-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.