Benchmark
RefCOCOg
RefCOCOg is a referring expression comprehension benchmark that evaluates spatial grounding in images. Given a natural language expression describing an…
- Modality
- multimodal
- Categories
- multimodal, grounding, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 1
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Nova 2 Omni | Amazon | 0.863 | 2025-12-02 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.