ScreenSpot-v2 Web
ScreenSpot-v2 Web as evaluated on the LFM3-VL-2B card (vision benchmark, with-thinking setting): GUI understanding category, with-thinking column. ScreenSpot-v2 web-platform split; only ScreenSpot-Pro is in the inventory.
Category
Vision & Language
Score type
percent
Scale
100%
higher is better
Models tested
1
What is ScreenSpot-v2 Web?
ScreenSpot-v2 Web is a benchmark for understanding images combined with text. The official description says: "ScreenSpot-v2 Web as evaluated on the LFM3-VL-2B card (vision benchmark, with-thinking setting): GUI understanding category, with-thinking column". Below we describe in simple words what benchmarks of this type generally examine.
What does it test?
ScreenSpot-v2 Web measures understanding images combined with text. In detail, it checks:
- answering questions about images (figures, photos, charts, memes)
- reading text inside images and connecting it to the question
- visual reasoning such as counting, locating and comparing objects
- combining what is seen with general knowledge
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: ScreenSpot-v2 Web as evaluated on the LFM3-VL-2B card (vision benchmark, with-thinking setting): GUI understanding category, with-thinking column. ScreenSpot-v2 web-platform split; only ScreenSpot-Pro is in the inventory.
Frequently asked questions
What is the ScreenSpot-v2 Web benchmark?
ScreenSpot-v2 Web is a benchmark for understanding images combined with text. The official description says: 'ScreenSpot-v2 Web as evaluated on the LFM3-VL-2B card (vision benchmark, with-thinking setting): GUI understanding category, with-thinking column'. Below we describe in simple words what benchmarks of this type generally examine.
What does ScreenSpot-v2 Web test?
ScreenSpot-v2 Web mainly measures understanding images combined with text. Concretely, it checks: answering questions about images (figures, photos, charts, memes); reading text inside images and connecting it to the question; visual reasoning such as counting, locating and comparing objects.
How is the ScreenSpot-v2 Web 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 ScreenSpot-v2 Web data and scores?
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/screenspot-v2-web/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.
Model scores 1 model tested
| # | Model | Score | Date | Source | Verified |
|---|---|---|---|---|---|
| 1 |
LFM3-VL-2B
LiquidAI
|
89.9%
|
— | Report | Verified |