Llama 2 70B Oasst Sft V10: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1417 ± 19, rank #5320 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Computer Science | 63 | Accuracy (%) | 100 |
| MMLU-by-task - International Law | 89.26 | Accuracy (%) | 99.9 |
| MMLU-by-task - Sociology | 90.05 | Accuracy (%) | 99.7 |
| MMLU-by-task - College Physics | 44.12 | Accuracy (%) | 99.6 |
| MMLU-by-task - High School Biology | 82.58 | Accuracy (%) | 98.6 |
| MMLU-by-task - Human Sexuality | 86.26 | Accuracy (%) | 98.3 |
| MMLU-by-task - High School Microeconomics | 77.31 | Accuracy (%) | 97.8 |
| MMLU-by-task - High School European History | 84.24 | Accuracy (%) | 97.5 |
| MMLU-by-task - High School Macroeconomics | 71.28 | Accuracy (%) | 96.8 |
| MMLU-by-task - High School Chemistry | 53.2 | Accuracy (%) | 96.4 |
| MMLU-by-task - High School Statistics | 59.26 | Accuracy (%) | 96.4 |
| MMLU-by-task - US Foreign Policy | 90 | Accuracy (%) | 96.3 |
Interactive version: theaggregate.ai/model?slug=llama-2-70b-oasst-sft-v10 · How It Works · Data refreshed daily, snapshot 2026-11-08.