multimodal benchmark
PointGrounding
PointArena is a comprehensive platform for evaluating multimodal pointing across diverse reasoning scenarios. It includes Point-Bench, a curated dataset of ~1,000 pointing tasks across five categories: Spatial (positional references), Affordance (functional part identification), Counting (attribute-based grouping), Steerable (relative pointing), and Reasoning (open-ended visual inference). The benchmark evaluates language-guided pointing capabilities in vision-language models.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
PointGrounding leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 66.5% | 100.0% | 1 | C |
PointGrounding highlights
The top published results on this benchmark's own scale.
What is PointGrounding?
Definition and scoring fields from the benchmark registry.
PointArena is a comprehensive platform for evaluating multimodal pointing across diverse reasoning scenarios. It includes Point-Bench, a curated dataset of ~1,000 pointing tasks across five categories: Spatial (positional references), Affordance (functional part identification), Counting (attribute-based grouping), Steerable (relative pointing), and Reasoning (open-ended visual inference). The benchmark evaluates language-guided pointing capabilities in vision-language models.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- PointGrounding
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- pointgrounding|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about PointGrounding.
Which model scores highest on PointGrounding?
Qwen2.5-Omni-7B is currently ranked first with 66.5%.
What does PointGrounding measure?
PointArena is a comprehensive platform for evaluating multimodal pointing across diverse reasoning scenarios. It includes Point-Bench, a curated dataset of ~1,000 pointing tasks across five categories: Spatial (positional references), Affordance (functional part identification), Counting (attribute-based grouping), Steerable (relative pointing), and Reasoning (open-ended visual inference). The benchmark evaluates language-guided pointing capabilities in vision-language models.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.