Synthia-13B: benchmark results
Provider: migtissera. Access: Open.
Aggregate Rating 1347 ± 15, rank #7784 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Mathematics | 41 | Accuracy (%) | 97.2 |
| MMLU-by-task - Moral Scenarios | 47.6 | Accuracy (%) | 92.6 |
| MMLU-by-task - Electrical Engineering | 54.48 | Accuracy (%) | 88.6 |
| MMLU-by-task - Logical Fallacies | 70.55 | Accuracy (%) | 87 |
| MMLU-by-task - World Religions | 79.53 | Accuracy (%) | 86.4 |
| MMLU-by-task - Formal Logic | 39.68 | Accuracy (%) | 85.5 |
| MMLU-by-task - Prehistory | 66.05 | Accuracy (%) | 84.1 |
| MMLU-by-task - Jurisprudence | 73.15 | Accuracy (%) | 84 |
| MMLU-by-task - College Computer Science | 48 | Accuracy (%) | 83.8 |
| MMLU-by-task - High School Psychology | 76.51 | Accuracy (%) | 82.9 |
| MMLU-by-task - High School World History | 76.79 | Accuracy (%) | 82.9 |
| MMLU-by-task - International Law | 74.38 | Accuracy (%) | 82 |
Interactive version: theaggregate.ai/model?slug=synthia-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.