Agents' Last Exam v1.1
Created by UC Berkeley RDI, 14 Oct 2026 · Higher is better · Website
- Other labs
Results
| Model | Score | Source | Source check |
|---|---|---|---|
| Kimi K3.1 Pro24 Oct 2026 · Moonshot AI | 44.2% | Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence86-task CLI subset; Kimi Code harness; max effort; runs that bypass task requirements scored zero |