Unholy-v1-12L-13B: benchmark results
Provider: Undi95. Access: Open.
Aggregate Rating 1360 ± 15, rank #7448 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 38 | Accuracy (%) | 96.5 |
| MMLU-by-task - High School Mathematics | 33.7 | Accuracy (%) | 94.7 |
| MMLU-by-task - Moral Scenarios | 48.16 | Accuracy (%) | 93.7 |
| MMLU-by-task - Jurisprudence | 78.7 | Accuracy (%) | 92.2 |
| MMLU-by-task - Human Aging | 69.51 | Accuracy (%) | 90.7 |
| MMLU-by-task - ARC Challenge | 61.43 | Accuracy (%) | 90.6 |
| MMLU-by-task - TruthfulQA MC1 | 36.96 | Accuracy (%) | 89.8 |
| MMLU-by-task - College Mathematics | 38 | Accuracy (%) | 89.5 |
| MMLU-by-task - US Foreign Policy | 85 | Accuracy (%) | 89.3 |
| MMLU-by-task - Electrical Engineering | 54.48 | Accuracy (%) | 88.6 |
| MMLU-by-task - Medical Genetics | 65 | Accuracy (%) | 88.5 |
| MMLU-by-task - College Biology | 65.97 | Accuracy (%) | 88.4 |
Interactive version: theaggregate.ai/model?slug=unholy-v1-12l-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.