multimodal benchmark
RefCOCOg Leaderboard
RefCOCOg is a referring expression comprehension benchmark that evaluates spatial grounding in images. Given a natural language expression describing an object, the model must localize the correct region, evaluated by accuracy at a 0.5 IoU threshold. It features longer, more descriptive expressions than RefCOCO and RefCOCO+.
Updated Aug 17, 2026
Models1
Model coverage1
MetricScore
EvidenceB
RefCOCOg Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAM Nova 2 OmniAmazon | Score86.3% | Percentile100.0% | Participants1 | EvidenceC | Evaluated |
RefCOCOg Highlights
The leading models and scores on this benchmark.
The Top AI Models for RefCOCOg
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis refcocog AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01AMNova 2 OmniAmazon
- Score
- 86.3%
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures RefCOCOg, not total model capability
Selection summary
Best AI Models for RefCOCOg
Nova 2 Omni currently leads RefCOCOg with 86.3%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is RefCOCOg?
What RefCOCOg measures and how its scores work.
RefCOCOg is a referring expression comprehension benchmark that evaluates spatial grounding in images. Given a natural language expression describing an object, the model must localize the correct region, evaluated by accuracy at a 0.5 IoU threshold. It features longer, more descriptive expressions than RefCOCO and RefCOCO+.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- RefCOCOg
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- refcocog|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about RefCOCOg.
Which model scores highest on RefCOCOg?
Nova 2 Omni is currently ranked first with 86.3%.
What does RefCOCOg measure?
RefCOCOg is a referring expression comprehension benchmark that evaluates spatial grounding in images. Given a natural language expression describing an object, the model must localize the correct region, evaluated by accuracy at a 0.5 IoU threshold. It features longer, more descriptive expressions than RefCOCO and RefCOCO+.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.