Llama 2 22B Blocktriangular: benchmark results
Provider: Meta.
Aggregate Rating 1340 ± 17, rank #7976 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 37 | Accuracy (%) | 94.5 |
| MMLU-by-task - Jurisprudence | 73.15 | Accuracy (%) | 84 |
| MMLU-by-task - College Computer Science | 48 | Accuracy (%) | 83.8 |
| MMLU-by-task - College Chemistry | 43 | Accuracy (%) | 83.5 |
| MMLU-by-task - US Foreign Policy | 83 | Accuracy (%) | 83.1 |
| MMLU-by-task - Nutrition | 62.42 | Accuracy (%) | 82.8 |
| MMLU-by-task - Computer Security | 70 | Accuracy (%) | 82.7 |
| MMLU-by-task - High School Chemistry | 44.33 | Accuracy (%) | 82.2 |
| MMLU-by-task - Moral Disputes | 64.16 | Accuracy (%) | 81.3 |
| MMLU-by-task - Electrical Engineering | 51.03 | Accuracy (%) | 79.8 |
| MMLU-by-task - Prehistory | 64.2 | Accuracy (%) | 79.1 |
| MMLU-by-task - World Religions | 77.19 | Accuracy (%) | 78.5 |
Interactive version: theaggregate.ai/model?slug=llama-2-22b-blocktriangular · How It Works · Data refreshed daily, snapshot 2026-11-08.