Harvey Legal Agent

Harvey Legal Agent is a benchmark for how well a model acts as a general-purpose agent. The official description says: "1,251 public tasks with Artificial Analysis's Stirrup harness; score is the all-pass rate over rubric criteria". Below we describe in simple words what benchmarks of this type generally examine.

Harvey Legal Agent 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: 1,251 public tasks with Artificial Analysis's Stirrup harness; score is the all-pass rate over rubric criteria.

What is the Harvey Legal Agent benchmark?

Harvey Legal Agent is a benchmark for how well a model acts as a general-purpose agent. The official description says: '1,251 public tasks with Artificial Analysis's Stirrup harness; score is the all-pass rate over rubric criteria'. Below we describe in simple words what benchmarks of this type generally examine.

What does Harvey Legal Agent test?

Harvey Legal Agent 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 Harvey Legal Agent 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 Harvey Legal Agent data and scores?

The official source is https://huggingface.co/moonshotai/Kimi-K3.1-Pro. 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/harvey-legal-agent/scores) or pull it directly from the Open LLM Radar API with any HTTP client.