GDPval-AA v2.1

GDPval-AA v2.1 is a benchmark for how well a model acts as a general-purpose agent. The official description says: "Elo-scored Artificial Analysis GDPval-AA v2.1 agent benchmark; distinct from GDPVal-AA v2 (index-typed) and plain GDPVal". Below we describe in simple words what benchmarks of this type generally examine.

GDPval-AA v2.1 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 an Elo rating, built from head-to-head comparisons between models (like chess ratings). The number is only meaningful relative to the other rated models — higher is better.

Official methodology note: Elo-scored Artificial Analysis GDPval-AA v2.1 agent benchmark; distinct from GDPVal-AA v2 (index-typed) and plain GDPVal.

What is the GDPval-AA v2.1 benchmark?

GDPval-AA v2.1 is a benchmark for how well a model acts as a general-purpose agent. The official description says: 'Elo-scored Artificial Analysis GDPval-AA v2.1 agent benchmark; distinct from GDPVal-AA v2 (index-typed) and plain GDPVal'. Below we describe in simple words what benchmarks of this type generally examine.

What does GDPval-AA v2.1 test?

GDPval-AA v2.1 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 GDPval-AA v2.1 score calculated?

The score is an Elo rating, built from head-to-head comparisons between models (like chess ratings). The number is only meaningful relative to the other rated models — higher is better.

Where do I get GDPval-AA v2.1 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/gdpval-aa-v2-1/scores) or pull it directly from the Open LLM Radar API with any HTTP client.