llama-30B-supercot: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1354 ± 15, rank #7584 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC2 | 53.96 | Accuracy (%) | 91.5 |
| MMLU-by-task - Medical Genetics | 67 | Accuracy (%) | 91.2 |
| MMLU-by-task - TruthfulQA MC1 | 37.58 | Accuracy (%) | 90.8 |
| MMLU-by-task - High School Geography | 78.28 | Accuracy (%) | 90.1 |
| MMLU-by-task - Anatomy | 54.07 | Accuracy (%) | 90 |
| MMLU-by-task - ARC Challenge | 61.01 | Accuracy (%) | 89.7 |
| MMLU-by-task - HellaSwag | 64.99 | Accuracy (%) | 89.1 |
| MMLU-by-task - Management | 77.67 | Accuracy (%) | 88.4 |
| MMLU-by-task - Conceptual Physics | 50.64 | Accuracy (%) | 87.7 |
| MMLU-by-task - High School European History | 73.33 | Accuracy (%) | 87.7 |
| MMLU-by-task - High School World History | 79.32 | Accuracy (%) | 87.4 |
| MMLU-by-task - Virology | 49.4 | Accuracy (%) | 87.4 |
Interactive version: theaggregate.ai/model?slug=llama-30b-supercot · How It Works · Data refreshed daily, snapshot 2026-11-08.