RefCOCO-M

RefCOCO-M is a benchmark for understanding images combined with text. The official description says: "RefCOCO-M as evaluated on the LFM3-VL-2B card (vision benchmark, with-thinking setting): Visual grounding category, with-thinking column". Below we describe in simple words what benchmarks of this type generally examine.

RefCOCO-M 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: RefCOCO-M as evaluated on the LFM3-VL-2B card (vision benchmark, with-thinking setting): Visual grounding category, with-thinking column. RefCOCO-M variant as printed by the card; distinct from the inventory's 'RefCOCO (avg)' record.

What is the RefCOCO-M benchmark?

RefCOCO-M is a benchmark for understanding images combined with text. The official description says: 'RefCOCO-M as evaluated on the LFM3-VL-2B card (vision benchmark, with-thinking setting): Visual grounding category, with-thinking column'. Below we describe in simple words what benchmarks of this type generally examine.

What does RefCOCO-M test?

RefCOCO-M 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 RefCOCO-M 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 RefCOCO-M 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/refcoco-m/scores) or pull it directly from the Open LLM Radar API with any HTTP client.