llama-13B-FINETUNE3: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1353 ± 15, rank #7618 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Mathematics | 34.81 | Accuracy (%) | 97.6 |
| MMLU-by-task - College Physics | 39.22 | Accuracy (%) | 96.7 |
| MMLU-by-task - College Chemistry | 49 | Accuracy (%) | 95.8 |
| MMLU-by-task - Professional Accounting | 51.77 | Accuracy (%) | 93.5 |
| MMLU-by-task - World Religions | 81.87 | Accuracy (%) | 91.2 |
| MMLU-by-task - High School Microeconomics | 63.87 | Accuracy (%) | 89.4 |
| MMLU-by-task - High School Statistics | 48.61 | Accuracy (%) | 88.2 |
| MMLU-by-task - High School Macroeconomics | 59.74 | Accuracy (%) | 88 |
| MMLU-by-task - High School US History | 80.88 | Accuracy (%) | 87.9 |
| MMLU-by-task - High School Psychology | 78.72 | Accuracy (%) | 87.4 |
| MMLU-by-task - Prehistory | 68.21 | Accuracy (%) | 87.3 |
| MMLU-by-task - Formal Logic | 40.48 | Accuracy (%) | 87.2 |
Interactive version: theaggregate.ai/model?slug=llama-13b-finetune3 · How It Works · Data refreshed daily, snapshot 2026-11-08.