OSWorld-G
OSWorld-G - scaled computer-use grounding benchmark via user interface decomposition and synthesis (NeurIPS 2025 Spotlight). Scores are measured on OSWorld-G tasks; repo: https://github.com/xlang-ai/OSWorld-G (paper: https://arxiv.org/abs/2505.13227).
Category
General Agents
Score type
percent
Scale
100%
higher is better
Models tested
3
What is OSWorld-G?
OSWorld-G is a benchmark for how well a model acts as a general-purpose agent. The official description says: "OSWorld-G - scaled computer-use grounding benchmark via user interface decomposition and synthesis (NeurIPS 2025 Spotlight)". Below we describe in simple words what benchmarks of this type generally examine.
What does it test?
OSWorld-G 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
How to read the score
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: OSWorld-G - scaled computer-use grounding benchmark via user interface decomposition and synthesis (NeurIPS 2025 Spotlight). Scores are measured on OSWorld-G tasks; repo: https://github.com/xlang-ai/OSWorld-G (paper: https://arxiv.org/abs/2505.13227).
Frequently asked questions
What is the OSWorld-G benchmark?
OSWorld-G is a benchmark for how well a model acts as a general-purpose agent. The official description says: 'OSWorld-G - scaled computer-use grounding benchmark via user interface decomposition and synthesis (NeurIPS 2025 Spotlight)'. Below we describe in simple words what benchmarks of this type generally examine.
What does OSWorld-G test?
OSWorld-G 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 OSWorld-G 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 OSWorld-G data and scores?
The official source is https://github.com/xlang-ai/OSWorld-G. 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/osworld-g/scores) or pull it directly from the Open LLM Radar API with any HTTP client.
Benchmark data & downloads
Where to get, inspect and reuse the data behind this benchmark.
Official benchmark page / paper
The benchmark maintainer's website, paper or leaderboard
Benchmark metadata (JSON)
This page's benchmark record from the Open LLM Radar API
All model scores (JSON download)
Full score table as JSON; paginate with limit/offset params
Open LLM Radar API docs
Swagger UI to explore and reuse all radar API endpoints
Model scores 3 models tested
| # | Model | Score | Date | Source | Verified |
|---|---|---|---|---|---|
| 1 |
Sage-S2.1-Flash
Shanghai AI Laboratory
|
84.8%
|
— | Report | Verified |
| 2 |
GLM-5.3-Flash
Zhipu AI
|
83.7%
|
— | Report | Unverified |
| 3 |
DeepSeek-V4.1-Flash-1017
DeepSeek
|
61.4%
|
— | Report | Unverified |