ReMM-v2.1-L2-13B: benchmark results
Provider: Undi95. Access: Open.
Aggregate Rating 1346 ± 15, rank #7793 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Moral Scenarios | 45.03 | Accuracy (%) | 89.5 |
| MMLU-by-task - TruthfulQA MC1 | 36.6 | Accuracy (%) | 88.6 |
| MMLU-by-task - HellaSwag | 64.69 | Accuracy (%) | 88.4 |
| MMLU-by-task - Jurisprudence | 75 | Accuracy (%) | 87.6 |
| MMLU-by-task - Human Aging | 67.71 | Accuracy (%) | 87.2 |
| MMLU-by-task - High School Mathematics | 31.85 | Accuracy (%) | 87 |
| MMLU-by-task - US Foreign Policy | 84 | Accuracy (%) | 86.5 |
| MMLU-by-task - Global Facts | 39 | Accuracy (%) | 85.7 |
| MMLU-by-task - Anatomy | 51.85 | Accuracy (%) | 85.2 |
| MMLU-by-task - ARC Challenge | 58.45 | Accuracy (%) | 84.4 |
| MMLU-by-task - Conceptual Physics | 48.09 | Accuracy (%) | 83.7 |
| MMLU-by-task - World Religions | 78.36 | Accuracy (%) | 83.1 |
Interactive version: theaggregate.ai/model?slug=remm-v2-1-l2-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.