Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Agentic benchmark
OSWorld 2.1 offline subset (82 tasks). Every model the catalog carries a published OSWorld 2.1 Offline value for, ranked by that value.
The official offline subset of OSWorld 2.1: 82 of the 108 long-horizon computer-use workflows, run with no internet access in the agent's virtual machine. 11 models in the ModelChoice catalog have a published value.
Each point is a model with a published OSWorld 2.1 Offline value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
11 models with a published OSWorld 2.1 Offline value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Interactive computer-use evaluation; partial score |
|---|---|---|---|
| 1 | Anthropic | 89.3 | |
| 2 | Anthropic | 87.2 | |
| 3 | Anthropic | 83.9 |
What the benchmark measures and how its value is published, from the source’s own record.
OSWorld 2.1 Offline (OSWorld 2.1 offline subset (82 tasks)) is an agentic benchmark published by OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1). The official offline subset of OSWorld 2.1: 82 of the 108 long-horizon computer-use workflows, run with no internet access in the agent's virtual machine. Its evaluation set is described by the source as 82 offline computer-use workflows. The source rates its difficulty as long-horizon professional workflows.
Each model's result is published by OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1) as interactive computer-use evaluation; partial score. ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 11 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 | Anthropic | 83.5 |
| 5 | 81.5 |
| 6 | 77.6 |
| 7 | 74.7 |
| 8 | OpenAI | 74.2 |
| 9 | Anthropic | 72.4 |
| 10 | OpenAI | 48.9 |
| 11 | Anthropic | 15.7 |
Evidence key: Observed
Rows are ordered by the value OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1) published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.