Llama 2 7B 32K Instruct: benchmark results
Provider: Meta. Released 2023-07-18. Access: Open.
Unified ELO 1283 ± 13, rank #1494 of 1639 rated models, from 76 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 33 | Accuracy (%) | 75.6 |
| MMLU-by-task - College Computer Science | 46 | Accuracy (%) | 75.6 |
| MMLU-by-task - Econometrics | 31.58 | Accuracy (%) | 73.2 |
| MMLU-by-task - College Mathematics | 34 | Accuracy (%) | 69.2 |
| MMLU-by-task - High School European History | 66.06 | Accuracy (%) | 66.7 |
| MMLU-by-task - Anatomy | 47.41 | Accuracy (%) | 61.3 |
| MMLU-by-task - High School Physics | 31.79 | Accuracy (%) | 61.3 |
| MMLU-by-task - TruthfulQA MC1 | 30.72 | Accuracy (%) | 61.3 |
| MMLU-by-task - Sociology | 66.67 | Accuracy (%) | 60.5 |
| MMLU-by-task - Elementary Mathematics | 30.69 | Accuracy (%) | 60.4 |
| MMLU-by-task - Conceptual Physics | 41.7 | Accuracy (%) | 60.3 |
| MMLU-by-task - High School Computer Science | 49 | Accuracy (%) | 59.1 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-32k-instruct · How It Works · Data refreshed daily, snapshot 2026-10-09.