llama-7B-SFT_ds_wiki65k_1024_r_64_alpha_16_merged: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1279 ± 15, rank #8987 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Machine Learning | 37.5 | Accuracy (%) | 71.9 |
| MMLU-by-task - Abstract Algebra | 32 | Accuracy (%) | 68.1 |
| MMLU-by-task - Professional Medicine | 51.84 | Accuracy (%) | 67.6 |
| MMLU-by-task - Philosophy | 58.84 | Accuracy (%) | 61.8 |
| MMLU-by-task - Virology | 42.77 | Accuracy (%) | 60.3 |
| MMLU-by-task - Formal Logic | 32.54 | Accuracy (%) | 59.5 |
| MMLU-by-task - Computer Security | 62 | Accuracy (%) | 58.8 |
| MMLU-by-task - Human Aging | 57.4 | Accuracy (%) | 58 |
| MMLU-by-task - Conceptual Physics | 40.85 | Accuracy (%) | 56.3 |
| MMLU-by-task - Electrical Engineering | 45.52 | Accuracy (%) | 56.2 |
| MMLU-by-task - High School Microeconomics | 44.54 | Accuracy (%) | 54.7 |
| MMLU-by-task - Professional Law | 36.83 | Accuracy (%) | 54 |
Interactive version: theaggregate.ai/model?slug=llama-7b-sft-ds-wiki65k-1024-r-64-alpha-16-merged · How It Works · Data refreshed daily, snapshot 2026-11-08.