AgentWorldBench OS

AgentWorldBench OS is a benchmark for how well a model acts as a general-purpose agent. The official description says: "AgentWorldBench OS domain - open-ended rubric evaluation for language world models simulating operating-system environments". Below we describe in simple words what benchmarks of this type generally examine.

AgentWorldBench OS 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: AgentWorldBench OS domain - open-ended rubric evaluation for language world models simulating operating-system environments. Normalized to 0-100.

What is the AgentWorldBench OS benchmark?

AgentWorldBench OS is a benchmark for how well a model acts as a general-purpose agent. The official description says: 'AgentWorldBench OS domain - open-ended rubric evaluation for language world models simulating operating-system environments'. Below we describe in simple words what benchmarks of this type generally examine.

What does AgentWorldBench OS test?

AgentWorldBench OS 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 AgentWorldBench OS 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 AgentWorldBench OS data and scores?

The official source is https://huggingface.co/Qwen/Qwen-AgentWorld-35B-A3B. 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/agentworldbench-os/scores) or pull it directly from the Open LLM Radar API with any HTTP client.