Meta
Comparing 2 models from Meta.
| Model | Total ▼ | Released | Context | CoT | Tooling | Creative Writing | Language | Utility | Reasoning | Text Editing | Rule Following | Hallucination |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Llama 3.1 70B | 78.40% | Jul 23, 24 | 128k | – | 88.59% | 72.78% | 80.18% | 81.03% | 79.31% | 92.10% | 63.45% | 69.78% |
| Llama 3.1 8B | 63.37% | Jul 23, 24 | 128k | – | 69.49% | 76.54% | 64.06% | 74.82% | 69.12% | 75.45% | 34.03% | 43.41% |
Model Performance
Cost vs Performance
Compares total benchmark cost against overall score for Meta models. Quadrant lines are drawn at the median values.
Cost Breakdown
Total benchmark cost per model, broken down by input, reasoning, and output tokens. Toggle between USD and token views.