AgentWorldBench Overall

AgentWorldBench Overall is a benchmark for how well a model acts as a general-purpose agent. The official description says: "AgentWorldBench Overall - mean across all 7 agent interaction domains (MCP, Search, Terminal, SWE, Android, Web, OS)". Below we describe in simple words what benchmarks of this type generally examine.

AgentWorldBench Overall 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 Overall - mean across all 7 agent interaction domains (MCP, Search, Terminal, SWE, Android, Web, OS). Five-dimensional rubric, normalized to 0-100.

What is the AgentWorldBench Overall benchmark?

AgentWorldBench Overall is a benchmark for how well a model acts as a general-purpose agent. The official description says: 'AgentWorldBench Overall - mean across all 7 agent interaction domains (MCP, Search, Terminal, SWE, Android, Web, OS)'. Below we describe in simple words what benchmarks of this type generally examine.

What does AgentWorldBench Overall test?

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