SkillsBench

SkillsBench is a benchmark for how well a model acts as a general-purpose agent. The official description says: "SkillsBench - evaluated on the public SkillsBench v1.1 benchmark across 87 tasks, reporting the average score over three runs per task". Below we describe in simple words what benchmarks of this type generally examine.

SkillsBench 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: SkillsBench - evaluated on the public SkillsBench v1.1 benchmark across 87 tasks, reporting the average score over three runs per task.

What is the SkillsBench benchmark?

SkillsBench is a benchmark for how well a model acts as a general-purpose agent. The official description says: 'SkillsBench - evaluated on the public SkillsBench v1.1 benchmark across 87 tasks, reporting the average score over three runs per task'. Below we describe in simple words what benchmarks of this type generally examine.

What does SkillsBench test?

SkillsBench 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 SkillsBench 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 SkillsBench 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/skillsbench/scores) or pull it directly from the Open LLM Radar API with any HTTP client.