multimodal benchmark
GroundUI-1K
A subset of GroundUI-18K for UI grounding evaluation, where models must predict action coordinates on screenshots based on single-step instructions across web, desktop, and mobile platforms.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
GroundUI-1K Ranking
Higher score ranks better on this benchmark.
| 1 | AM Nova ProAmazon | 81.4% | 100.0% | 2 | C | |
| 2 | AMNova LiteAmazon | 80.2% | 0.0% | 2 | C |
GroundUI-1K Score Distribution
A closer view of the leading scores on this benchmark.
GroundUI-1K Highlights
The leading models and scores on this benchmark.
What is GroundUI-1K?
What GroundUI-1K measures and how its scores work.
A subset of GroundUI-18K for UI grounding evaluation, where models must predict action coordinates on screenshots based on single-step instructions across web, desktop, and mobile platforms.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- GroundUI-1K
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- groundui-1k|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about GroundUI-1K.
Which model scores highest on GroundUI-1K?
Nova Pro is currently ranked first with 81.4%.
What does GroundUI-1K measure?
A subset of GroundUI-18K for UI grounding evaluation, where models must predict action coordinates on screenshots based on single-step instructions across web, desktop, and mobile platforms.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 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.