Llama 2 7B Base Flan2022 1.2M: benchmark results
Provider: Meta.
Aggregate Rating 1263 ± 16, rank #9137 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Professional Accounting | 39.36 | Accuracy (%) | 66.8 |
| MMLU-by-task - Business Ethics | 53 | Accuracy (%) | 66.1 |
| MMLU-by-task - Computer Security | 63 | Accuracy (%) | 60.8 |
| MMLU-by-task - Conceptual Physics | 41.7 | Accuracy (%) | 60.3 |
| MMLU-by-task - Moral Scenarios | 27.26 | Accuracy (%) | 59.8 |
| MMLU-by-task - Professional Medicine | 49.26 | Accuracy (%) | 57.9 |
| MMLU-by-task - Philosophy | 55.63 | Accuracy (%) | 54.9 |
| MMLU-by-task - Professional Psychology | 46.57 | Accuracy (%) | 54.1 |
| MMLU-by-task - Elementary Mathematics | 29.1 | Accuracy (%) | 52.4 |
| MMLU-by-task - Abstract Algebra | 30 | Accuracy (%) | 52.2 |
| MMLU-by-task - Security Studies | 50.61 | Accuracy (%) | 51.2 |
| MMLU-by-task - High School Macroeconomics | 43.08 | Accuracy (%) | 50.6 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-base-flan2022-1-2m · How It Works · Data refreshed daily, snapshot 2026-11-08.