Point-Bench

Point-Bench is a benchmark for understanding where things are in space. The official description says: "Point-Bench 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.

Point-Bench measures understanding where things are in space. In detail, it checks:

• locating and pointing to regions in images
• reasoning about positions, counts and relations between objects
• 3D-aware questions such as depth, perspective and room layout
• grounded perception tasks that must stay anchored to pixel locations

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: Point-Bench as evaluated on the LFM3-VL-2B card (vision benchmark, with-thinking setting): Visual grounding category, with-thinking column. Pointing benchmark; no inventory match.

What is the Point-Bench benchmark?

Point-Bench is a benchmark for understanding where things are in space. The official description says: 'Point-Bench 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 Point-Bench test?

Point-Bench mainly measures understanding where things are in space. Concretely, it checks: locating and pointing to regions in images; reasoning about positions, counts and relations between objects; 3D-aware questions such as depth, perspective and room layout.

How is the Point-Bench 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 Point-Bench 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/point-bench/scores) or pull it directly from the Open LLM Radar API with any HTTP client.