multimodal benchmark
ScreenSpot
ScreenSpot is the first realistic GUI grounding benchmark that encompasses mobile, desktop, and web environments. The dataset comprises over 1,200 instructions from iOS, Android, macOS, Windows and Web environments, along with annotated element types (text and icon/widget), designed to evaluate visual GUI agents' ability to accurately locate screen elements based on natural language instructions.
Updated Aug 11, 2026
Models16
Model coverage16
MetricScore
EvidenceB
ScreenSpot Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 95.8% | 100.0% | 16 | C | |
| 02 | AC | 95.7% | 93.3% | 16 | C | |
| 03 | AC | 95.4% | 86.7% | 16 | C | |
| 04 | AC | 95.4% | 80.0% | 16 | C | |
| 05 | AC | 94.7% | 73.3% | 16 | C | |
| 06 | AC | 94.7% | 66.7% | 16 | C | |
| 07 | AC | 94.4% | 60.0% | 16 | C | |
| 08 | AC | 94.0% | 53.3% | 16 | C | |
| 09 | AC | 93.6% | 46.7% | 16 | C | |
| 10 | AC | 92.9% | 40.0% | 16 | C | |
| 11 | AC | 88.5% | 33.3% | 16 | C | |
| 12 | AM Nova 2 ProAmazon | 88.1% | 26.7% | 16 | C | |
| 13 | AC | 87.1% | 20.0% | 16 | C | |
| 14 | AMNova 2 OmniAmazon | 85.4% | 13.3% | 16 | C | |
| 15 | AC | 84.7% | 6.7% | 16 | C | |
| 16 | AMNova 2 LiteAmazon | 83.3% | 0.0% | 16 | C |
ScreenSpot Score Distribution
A closer view of the leading scores on this benchmark.
ScreenSpot Highlights
The leading models and scores on this benchmark.
What is ScreenSpot?
What ScreenSpot measures and how its scores work.
ScreenSpot is the first realistic GUI grounding benchmark that encompasses mobile, desktop, and web environments. The dataset comprises over 1,200 instructions from iOS, Android, macOS, Windows and Web environments, along with annotated element types (text and icon/widget), designed to evaluate visual GUI agents' ability to accurately locate screen elements based on natural language instructions.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- ScreenSpot
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- screenspot|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about ScreenSpot.
Which model scores highest on ScreenSpot?
Qwen3 VL 32B Instruct is currently ranked first with 95.8%.
What does ScreenSpot measure?
ScreenSpot is the first realistic GUI grounding benchmark that encompasses mobile, desktop, and web environments. The dataset comprises over 1,200 instructions from iOS, Android, macOS, Windows and Web environments, along with annotated element types (text and icon/widget), designed to evaluate visual GUI agents' ability to accurately locate screen elements based on natural language instructions.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
16 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.