AutomationBench
agents and tool use.
agents and tool useactive
Definition
- Version
- not in the notes
- Category
- agents and tool use
- Maintainer
- not in the notes
- Status
- active
- Home page
- not in the notes
Sources
- Gemini 4 Argon: qué anunció Google y qué significa el nombre orcarouter.ai https://www.orcarouter.ai/es/blog/gemini-4-argon
Scores
| Model | Score | Who ran it | Setting | View or population | Date | Source |
|---|---|---|---|---|---|---|
 MiMo-V2.6-Flash | 52.3 % | vendor-reported | AutomationBench v1.0.6 | MiMo-V2.6 model card comparison table | 21 Sep 2026 | huggingface.co |
 Gemini 4 Argon | 51.3 % | vendor-reported | Google self-reported | – | – | orcarouter.ai |
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "AutomationBench", https://aurion.semai.id/benchmarks/automationbench/, records of October 2026.