Automation-Bench

Automation-Bench is a benchmark for how well a model acts as a general-purpose agent. The official description says: "Automation-Bench - evaluated on the 600-task public subset". Below we describe in simple words what benchmarks of this type generally examine.

Automation-Bench measures how well a model acts as a general-purpose agent. In detail, it checks:

• solving long, multi-step tasks with many intermediate decisions
• using tools correctly (browsers, terminals, APIs, calendars, other apps)
• adapting when something unexpected happens mid-task
• staying on goal over long task horizons instead of wandering off

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: Automation-Bench - evaluated on the 600-task public subset. Pass@1 score.

What is the Automation-Bench benchmark?

Automation-Bench is a benchmark for how well a model acts as a general-purpose agent. The official description says: 'Automation-Bench - evaluated on the 600-task public subset'. Below we describe in simple words what benchmarks of this type generally examine.

What does Automation-Bench test?

Automation-Bench mainly measures how well a model acts as a general-purpose agent. Concretely, it checks: solving long, multi-step tasks with many intermediate decisions; using tools correctly (browsers, terminals, APIs, calendars, other apps); adapting when something unexpected happens mid-task.

How is the Automation-Bench score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Where do I get Automation-Bench data and scores?

The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/automation-bench/scores) or pull it directly from the Open LLM Radar API with any HTTP client.