MLewd-L2-Chat-13B: benchmark results
Provider: Undi95. Access: Open.
Aggregate Rating 1363 ± 15, rank #7346 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 41 | Accuracy (%) | 99.5 |
| MMLU-by-task - High School Mathematics | 34.07 | Accuracy (%) | 96 |
| MMLU-by-task - Moral Scenarios | 50.28 | Accuracy (%) | 95.1 |
| MMLU-by-task - Formal Logic | 45.24 | Accuracy (%) | 93.2 |
| MMLU-by-task - Jurisprudence | 79.63 | Accuracy (%) | 92.9 |
| MMLU-by-task - TruthfulQA MC1 | 38.07 | Accuracy (%) | 92 |
| MMLU-by-task - US Foreign Policy | 86 | Accuracy (%) | 91.5 |
| MMLU-by-task - Medical Genetics | 67 | Accuracy (%) | 91.2 |
| MMLU-by-task - Human Aging | 69.06 | Accuracy (%) | 90.3 |
| MMLU-by-task - College Biology | 66.67 | Accuracy (%) | 89.5 |
| MMLU-by-task - TruthfulQA MC2 | 52.84 | Accuracy (%) | 89.2 |
| MMLU-by-task - Clinical Knowledge | 63.4 | Accuracy (%) | 88.9 |
Interactive version: theaggregate.ai/model?slug=mlewd-l2-chat-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.