multimodal benchmark
OSWorld-G
OSWorld-G (Grounding) evaluates screenshot grounding accuracy for OS automation tasks.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
OSWorld-G Ranking
Higher score ranks better on this benchmark.
| 1 | AC | 0.683 points | 100.0% | 1 | C |
OSWorld-G Highlights
The leading models and scores on this benchmark.
What is OSWorld-G?
What OSWorld-G measures and how its scores work.
OSWorld-G (Grounding) evaluates screenshot grounding accuracy for OS automation tasks.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- OSWorld-G
- Modality
- image
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- osworld-g|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about OSWorld-G.
Which model scores highest on OSWorld-G?
Qwen3 VL 235B A22B Thinking is currently ranked first with 0.683 points.
What does OSWorld-G measure?
OSWorld-G (Grounding) evaluates screenshot grounding accuracy for OS automation tasks.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.