ZEROBench

ZEROBench is a benchmark for understanding images combined with text. The official description says: "ZEROBench - visual reasoning puzzle benchmark". Below we describe in simple words what benchmarks of this type generally examine.

ZEROBench 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

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: ZEROBench - visual reasoning puzzle benchmark. Very challenging, scores typically in single digits.

What is the ZEROBench benchmark?

ZEROBench is a benchmark for understanding images combined with text. The official description says: 'ZEROBench - visual reasoning puzzle benchmark'. Below we describe in simple words what benchmarks of this type generally examine.

What does ZEROBench test?

ZEROBench 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 ZEROBench score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Where do I get ZEROBench 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/zerobench/scores) or pull it directly from the Open LLM Radar API with any HTTP client.