About Agents Last Exam
Definition and scoring
- Organisation
- UC Berkeley RDI
- Category
- Knowledge
- Version
- 2026
- Direction
- higher is better
- Ranking use
- Reference
- Contamination risk
- Unknown
A benchmark for agentic professional workflows with verifiable success criteria, reporting pass rates and partial scores for model plus agent-harness rows. 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 ↗