Llama 2 70B Fb16 Orca Chat 10k: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1433 ± 17, rank #4508 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - International Law | 88.43 | Accuracy (%) | 99.5 |
| MMLU-by-task - Professional Psychology | 76.47 | Accuracy (%) | 99.3 |
| MMLU-by-task - Prehistory | 83.95 | Accuracy (%) | 99 |
| MMLU-by-task - Marketing | 91.03 | Accuracy (%) | 98.7 |
| MMLU-by-task - Philosophy | 78.14 | Accuracy (%) | 98.6 |
| MMLU-by-task - World Religions | 87.13 | Accuracy (%) | 98.5 |
| MMLU-by-task - Security Studies | 80 | Accuracy (%) | 98.1 |
| MMLU-by-task - TruthfulQA MC1 | 43.94 | Accuracy (%) | 98 |
| MMLU-by-task - TruthfulQA MC2 | 61.56 | Accuracy (%) | 98 |
| MMLU-by-task - High School Macroeconomics | 71.79 | Accuracy (%) | 97.8 |
| MMLU-by-task - Conceptual Physics | 67.66 | Accuracy (%) | 97.7 |
| MMLU-by-task - Electrical Engineering | 63.45 | Accuracy (%) | 97.7 |
Interactive version: theaggregate.ai/model?slug=llama-2-70b-fb16-orca-chat-10k · How It Works · Data refreshed daily, snapshot 2026-11-08.