Metharme-13B-Merged: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1299 ± 16, rank #8749 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC1 | 36.96 | Accuracy (%) | 89.8 |
| MMLU-by-task - Formal Logic | 39.68 | Accuracy (%) | 85.5 |
| MMLU-by-task - TruthfulQA MC2 | 51.18 | Accuracy (%) | 81.5 |
| MMLU-by-task - ARC Challenge | 57.34 | Accuracy (%) | 80.2 |
| MMLU-by-task - Machine Learning | 38.39 | Accuracy (%) | 75.5 |
| MMLU-by-task - International Law | 70.25 | Accuracy (%) | 68.5 |
| MMLU-by-task - US Foreign Policy | 77 | Accuracy (%) | 65.8 |
| MMLU-by-task - HellaSwag | 61.22 | Accuracy (%) | 65.5 |
| MMLU-by-task - Professional Psychology | 50.82 | Accuracy (%) | 63.2 |
| MMLU-by-task - Professional Law | 39.31 | Accuracy (%) | 63.1 |
| MMLU-by-task - Sociology | 67.16 | Accuracy (%) | 61.3 |
| MMLU-by-task - Logical Fallacies | 57.67 | Accuracy (%) | 60.8 |
Interactive version: theaggregate.ai/model?slug=metharme-13b-merged · How It Works · Data refreshed daily, snapshot 2026-11-08.