Llama 2 7B Int4 Python Code 18k: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1285 ± 15, rank #8921 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Mathematics | 35 | Accuracy (%) | 75 |
| MMLU-by-task - Abstract Algebra | 32 | Accuracy (%) | 68.1 |
| MMLU-by-task - Conceptual Physics | 42.98 | Accuracy (%) | 68.1 |
| MMLU-by-task - Machine Learning | 36.61 | Accuracy (%) | 68 |
| MMLU-by-task - High School Mathematics | 28.89 | Accuracy (%) | 67.8 |
| MMLU-by-task - Anatomy | 48.15 | Accuracy (%) | 66.5 |
| MMLU-by-task - Professional Medicine | 51.47 | Accuracy (%) | 65.5 |
| MMLU-by-task - Medical Genetics | 56 | Accuracy (%) | 65.3 |
| MMLU-by-task - Philosophy | 59.81 | Accuracy (%) | 64.1 |
| MMLU-by-task - Business Ethics | 51 | Accuracy (%) | 58.6 |
| MMLU-by-task - Sociology | 64.18 | Accuracy (%) | 56 |
| MMLU-by-task - High School Government And Politics | 68.39 | Accuracy (%) | 55.9 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-int4-python-code-18k · How It Works · Data refreshed daily, snapshot 2026-11-08.