OPT-30B-Erebus: benchmark results
Provider: KoboldAI. Access: Open.
Aggregate Rating 1135 ± 16, rank #10208 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 31 | Accuracy (%) | 60.2 |
| MMLU-by-task - Formal Logic | 30.95 | Accuracy (%) | 52.2 |
| MMLU-by-task - Machine Learning | 32.14 | Accuracy (%) | 48.9 |
| MMLU-by-task - Econometrics | 27.19 | Accuracy (%) | 39.6 |
| MMLU-by-task - High School Statistics | 31.94 | Accuracy (%) | 35.8 |
| MMLU-by-task - Jurisprudence | 30.56 | Accuracy (%) | 31.6 |
| MMLU-by-task - High School World History | 29.54 | Accuracy (%) | 31 |
| MMLU-by-task - Anatomy | 31.85 | Accuracy (%) | 29.1 |
| MMLU-by-task - High School Biology | 29.35 | Accuracy (%) | 28.7 |
| MMLU-by-task - Human Sexuality | 27.48 | Accuracy (%) | 27.3 |
| MMLU-by-task - HellaSwag | 48.59 | Accuracy (%) | 26.8 |
| MMLU-by-task - Nutrition | 27.78 | Accuracy (%) | 25.8 |
Interactive version: theaggregate.ai/model?slug=opt-30b-erebus · How It Works · Data refreshed daily, snapshot 2026-11-08.