CoWorkBench

CoWorkBench is a benchmark for how well a model acts as a general-purpose agent. The official description says: "CoWorkBench - in-house cowork benchmark for evaluating long-horizon tasks across computer science, finance, law, medical, and other productivity domains". Below we describe in simple words what benchmarks of this type generally examine.

CoWorkBench 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: CoWorkBench - in-house cowork benchmark for evaluating long-horizon tasks across computer science, finance, law, medical, and other productivity domains.

What is the CoWorkBench benchmark?

CoWorkBench is a benchmark for how well a model acts as a general-purpose agent. The official description says: 'CoWorkBench - in-house cowork benchmark for evaluating long-horizon tasks across computer science, finance, law, medical, and other productivity domains'. Below we describe in simple words what benchmarks of this type generally examine.

What does CoWorkBench test?

CoWorkBench 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 CoWorkBench score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get CoWorkBench 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/coworkbench/scores) or pull it directly from the Open LLM Radar API with any HTTP client.