AgentWorldBench Search

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

AgentWorldBench Search 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 Search domain - open-ended rubric evaluation for language world models simulating search environments. Normalized to 0-100.

What is the AgentWorldBench Search benchmark?

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

What does AgentWorldBench Search test?

AgentWorldBench Search 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 Search 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 Search 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-search/scores) or pull it directly from the Open LLM Radar API with any HTTP client.