VisualPuzzles
VisualPuzzles, visual reasoning puzzle benchmark. Values reported as percentage. Source referenced on the LiquidAI/d1-2B model card.
Category
Vision & Language
Score type
percent
Scale
100%
higher is better
Models tested
1
What is VisualPuzzles?
VisualPuzzles is a benchmark for understanding images combined with text. The official description says: "VisualPuzzles, visual reasoning puzzle benchmark". Below we describe in simple words what benchmarks of this type generally examine.
What does it test?
VisualPuzzles 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: VisualPuzzles, visual reasoning puzzle benchmark. Values reported as percentage. Source referenced on the LiquidAI/d1-2B model card.
Frequently asked questions
What is the VisualPuzzles benchmark?
VisualPuzzles is a benchmark for understanding images combined with text. The official description says: 'VisualPuzzles, visual reasoning puzzle benchmark'. Below we describe in simple words what benchmarks of this type generally examine.
What does VisualPuzzles test?
VisualPuzzles 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 VisualPuzzles 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 VisualPuzzles 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/visualpuzzles/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 |
d1-2B
LiquidAI
|
29.9%
|
— | LiquidAI/d1-2B model card (performance table) | Unverified |