Help keep public data accurate
See something missing, incorrect, or out of date? Tell us about this page.
See something missing, incorrect, or out of date? Tell us about this page.
AI benchmark results and model performance
Individual benchmark scores plotted by date.
| Organisation | Models | Reported | Top score | Info | Self reported | Source |
|---|---|---|---|---|---|---|
| Muse Ember 1.0 | 09 Nov 2026 | 46.80% | Meta internal composite of 8 evals (Agents' Last Exam, AutomationBench, FocusBench, JobBench, OfficeQA Pro, GDP.pdf, GDP.xlsx, VBT); reasoning effort max; Meta-reported in the Muse Ember launch post (accessed 2026-11-09) | Yes | Source |
