About TheAgentCompany
Definition and scoring
- Organisation
- TheAgentCompany
- Category
- Agents
- Version
- Not evaluated
- Direction
- higher is better
- Ranking use
- Reference
- Contamination risk
- Low
Realistic office-work agent evaluation where models complete multi-day digital workplace tasks using browsers, docs, and internal tools. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗