Petroc Taylor
Research expert covering global developments in the use of data
Get in touch with us now| Characteristic | APEX-Agents score* |
|---|---|
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
The chart is not accessible to screen readers. Please switch to the table view to access the data.
Download
Source
Source
Release date
February 2026
More information
Region
Worldwide
Survey time period
2026
Supplementary notes
* The APEX-Agents benchmark evaluates how well AI agents can perform realistic professional tasks that may involve using files and tools such as documents, spreadsheets, PDFs, email, chat, and calendars. For each assignment, the model must satisfy a set of predefined criteria. The reported percentage represents the probability that a randomly selected task is completed correctly on a single attempt (Pass@1).
Citation formats
