Microsoft
Comparing 1 model from Microsoft.
| Model | Total ▼ | Released | Context | CoT | Tooling | Creative Writing | Language | Utility | Reasoning | Text Editing | Rule Following | Hallucination |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| WizardLM 2 8x22b | 71.07% | Apr 15, 24 | 65k | – | 90.27% | 79.06% | 78.05% | 67.14% | 67.36% | 88.13% | 28.27% | 70.24% |
Cost Breakdown
Total benchmark cost per model, broken down by input, reasoning, and output tokens. Toggle between USD and token views.