# Referring Expression Grounding on RefCOCOg (test)

Source: [Referring Expression Grounding on RefCOCOg (test)](<https://www.sota2.com/research/sota/referring-expression-grounding-on-refcocog-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-09T10:39:27.998Z

Evaluation of Referring Expression Grounding performance on the test split of the RefCOCOg dataset, reporting Accuracy and Average Accuracy.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Referring Expression Grounding |
| Dataset (including any stated split) | RefCOCOg (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 50 of 50 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/referring-expression-grounding-on-refcocog-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/referring-expression-grounding-on-refcocog-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

- [Score](<https://www.sota2.com/research/sota/referring-expression-grounding-on-refcocog-test.md?metric=Score>): Higher is better; unit: PERCENT.

- [Accuracy@0.5](<https://www.sota2.com/research/sota/referring-expression-grounding-on-refcocog-test.md?metric=Accuracy%400.5>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Ferret-V2-13B | 90 | Not recorded | 68fa75051e209131cea65504 |
| MM1.5-30B | 90 | Not recorded | 68fa75051e209131cea65504 |
| Ferret-V2-7B | 89.3 | Not recorded | 68fa75051e209131cea65504 |
| MM1.5-7B | 87.1 | Not recorded | 68fa75051e209131cea65504 |
| G-DINO | 87 | Not recorded | 68fa78f11e209131cea7b594 |
| MM1.5-3B | 86.4 | Not recorded | 68fa75051e209131cea65504 |
| MM1.5-3B-MoE | 86.4 | Not recorded | 68fa75051e209131cea65504 |
| Qwen-VL-7B | 86.3 | Not recorded | 68fa75051e209131cea65504 |
| Ferret-13B | 86.3 | Not recorded | 68fa75051e209131cea65504 |
| QwenVL-7B | 85.5 | Not recorded | 68fa78f11e209131cea7b594 |
| Argus-X3-8B | 85.2 | Not recorded | 68fa78f11e209131cea7b594 |
| Ferret-7B | 84.8 | Not recorded | 68fa75051e209131cea65504 |
| Ferret-7B | 84.8 | Not recorded | 68fa78f11e209131cea7b594 |
| MM1.5-1B-MoE | 84.7 | Not recorded | 68fa75051e209131cea65504 |
| MiniGPT-7B | 84.7 | Not recorded | 68fa78f11e209131cea7b594 |
| MiniGPT-v2-7B | 84.3 | Not recorded | 68fa75051e209131cea65504 |
| MM1.5-1B | 82.8 | Not recorded | 68fa75051e209131cea65504 |
| InternVL2-8B | 82.7 | Not recorded | 68fa78f11e209131cea7b594 |
| Shikra-7B | 82.2 | Not recorded | 68fa78f11e209131cea7b594 |
| MDETR | 80.9 | Not recorded | 68fa78f11e209131cea7b594 |
| UniTAB | 80 | Not recorded | 68fa78f11e209131cea7b594 |
| SPHINX-Tiny | 78.9 | Not recorded | 68fa75051e209131cea65504 |
| InternVL2 | 78.3 | Not recorded | 68fa75051e209131cea65504 |
| VILLA | 76.7 | Not recorded | 68fa78f11e209131cea7b594 |
| Iterative Shrinking | 70.05 | Not recorded | 68fa697c1e209131cea22600 |
| LLaVA-OneVision-7B | 70 | Not recorded | 68fa75051e209131cea65504 |
| UNITER | 68.7 | Not recorded | 68fa78f11e209131cea7b594 |
| TransVG | 67.7 | Not recorded | 68fa78f11e209131cea7b594 |
| OFA-L | 67.6 | Not recorded | 68fa78f11e209131cea7b594 |
| MAttNet | 67.01 | Not recorded | 68fa697c1e209131cea22600 |
| MAttNet | 67 | Not recorded | 68fa78f11e209131cea7b594 |
| RCCF | 65.73 | Not recorded | 68fa697c1e209131cea22600 |
| DGA | 63.28 | Not recorded | 68fa697c1e209131cea22600 |
| MCN | 62.29 | Not recorded | 68fa697c1e209131cea22600 |
| SLR | 59.63 | Not recorded | 68fa697c1e209131cea22600 |
| FAOAVG | 57.45 | Not recorded | 68fa697c1e209131cea22600 |
| Phi-3-Vision-4B | 37.6 | Not recorded | 68fa75051e209131cea65504 |

### Ferret-V2-13B

Accuracy: 90. Result ID: 699370673a6c31484915efcd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72df1e209131cea5914a.md>)

Recorded evaluation configuration: {"Model Size Category":"Larger (\>13B)"}. This record does not assert independent reproduction.

### MM1.5-30B

Accuracy: 90. Result ID: 699370673a6c31484915efce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Model Size Category":"Larger (\>13B)"}. This record does not assert independent reproduction.

### Ferret-V2-7B

Accuracy: 89.3. Result ID: 699370673a6c31484915efca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72df1e209131cea5914a.md>)

Recorded evaluation configuration: {"Model Size Category":"7B"}. This record does not assert independent reproduction.

### MM1.5-7B

Accuracy: 87.1. Result ID: 699370673a6c31484915efcb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Model Size Category":"7B"}. This record does not assert independent reproduction.

### G-DINO

Accuracy: 87. Result ID: 6995b0fa3badfaffe6b082b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74311e209131cea6055d.md>)

[Implementation](<https://github.com/IDEA-Research/GroundingDINO>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MM1.5-3B

Accuracy: 86.4. Result ID: 699370673a6c31484915efc4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Model Size Category":"3B"}. This record does not assert independent reproduction.

### MM1.5-3B-MoE

Accuracy: 86.4. Result ID: 699370673a6c31484915efc5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Model Size Category":"3B","Architecture":"MoE"}. This record does not assert independent reproduction.

### Qwen-VL-7B

Accuracy: 86.3. Result ID: 699370673a6c31484915efc6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d41e209131cea4d774.md>)

[Implementation](<https://github.com/QwenLM/Qwen-VL>)

Recorded evaluation configuration: {"Model Size Category":"7B"}. This record does not assert independent reproduction.

### Ferret-13B

Accuracy: 86.3. Result ID: 699370673a6c31484915efcc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d81e209131cea4da64.md>)

Recorded evaluation configuration: {"Model Size Category":"Larger (\>13B)"}. This record does not assert independent reproduction.

### QwenVL-7B

Accuracy: 85.5. Result ID: 6995b0fa3badfaffe6b082bf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d41e209131cea4d774.md>)

[Implementation](<https://github.com/QwenLM/Qwen-VL>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Argus-X3-8B

Accuracy: 85.2. Result ID: 6995b0fa3badfaffe6b082c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Implementation](<https://yunzeman.github.io/argus/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Ferret-7B

Accuracy: 84.8. Result ID: 699370673a6c31484915efc9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d81e209131cea4da64.md>)

Recorded evaluation configuration: {"Model Size Category":"7B"}. This record does not assert independent reproduction.

### Ferret-7B

Accuracy: 84.8. Result ID: 6995b0fa3badfaffe6b082bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d81e209131cea4da64.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MM1.5-1B-MoE

Accuracy: 84.7. Result ID: 699370673a6c31484915efc1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Model Size Category":"1B","Architecture":"MoE"}. This record does not assert independent reproduction.

### MiniGPT-7B

Accuracy: 84.7. Result ID: 6995b0fa3badfaffe6b082bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71251e209131cea4f7e5.md>)

[Implementation](<https://minigpt-v2.github.io/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MiniGPT-v2-7B

Accuracy: 84.3. Result ID: 699370673a6c31484915efc7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71251e209131cea4f7e5.md>)

[Implementation](<https://minigpt-v2.github.io/>)

Recorded evaluation configuration: {"Model Size Category":"7B"}. This record does not assert independent reproduction.

### MM1.5-1B

Accuracy: 82.8. Result ID: 699370673a6c31484915efc0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Implementation](<https://github.com/apple/axlearn>)

Recorded evaluation configuration: {"Model Size Category":"1B"}. This record does not assert independent reproduction.

### InternVL2-8B

Accuracy: 82.7. Result ID: 6995b0fa3badfaffe6b082be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Shikra-7B

Accuracy: 82.2. Result ID: 6995b0fa3badfaffe6b082bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fe61e209131cea47fbc.md>)

[Implementation](<https://github.com/shikras/shikra>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MDETR

Accuracy: 80.9. Result ID: 6995b0fa3badfaffe6b082b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af51e209131cea2b5a9.md>)

[Implementation](<https://github.com/ashkamath/mdetr>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### UniTAB

Accuracy: 80. Result ID: 6995b0fa3badfaffe6b082b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1f1e209131cea37ecb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SPHINX-Tiny

Accuracy: 78.9. Result ID: 699370673a6c31484915efbf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77961e209131cea74290.md>)

[Implementation](<https://github.com/Alpha-VLLM/LLaMA2-Accessory>)

Recorded evaluation configuration: {"Model Size Category":"1B"}. This record does not assert independent reproduction.

### InternVL2

Accuracy: 78.3. Result ID: 699370673a6c31484915efc3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73081e209131cea59f8b.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

Recorded evaluation configuration: {"Model Size Category":"3B"}. This record does not assert independent reproduction.

### VILLA

Accuracy: 76.7. Result ID: 6995b0fa3badfaffe6b082b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d368.md>)

[Implementation](<https://github.com/zhegan27/VILLA>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Iterative Shrinking

Accuracy: 70.05. Result ID: 698dae9e8b517eb4332318e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea22600.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea22600.md>)

[Implementation](<https://github.com/insomnia94/ISREG>)

Recorded evaluation configuration: {"Proposal-free":true,"Visual Extractor":"ResNet-101"}. This record does not assert independent reproduction.

### LLaVA-OneVision-7B

Accuracy: 70. Result ID: 699370673a6c31484915efc8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74ae1e209131cea632e1.md>)

Recorded evaluation configuration: {"Model Size Category":"7B"}. This record does not assert independent reproduction.

### UNITER

Accuracy: 68.7. Result ID: 6995b0fa3badfaffe6b082b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67f91e209131cea1989f.md>)

[Implementation](<https://github.com/ChenRocks/UNITER>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TransVG

Accuracy: 67.7. Result ID: 6995b0fa3badfaffe6b082b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b941e209131cea2f03e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### OFA-L

Accuracy: 67.6. Result ID: 6995b0fa3badfaffe6b082ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb81e209131cea35951.md>)

[Implementation](<https://github.com/OFA-Sys/OFA>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MAttNet

Accuracy: 67.01. Result ID: 698dae9e8b517eb4332318e3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea22600.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa642c1e209131cea031d4.md>)

[Implementation](<https://github.com/lichengunc/MAttNet>)

Recorded evaluation configuration: {"Proposal-free":false,"Visual Extractor":"ResNet-101"}. This record does not assert independent reproduction.

### MAttNet

Accuracy: 67. Result ID: 6995b0fa3badfaffe6b082b3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f11e209131cea7b594.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa642c1e209131cea031d4.md>)

[Implementation](<https://github.com/lichengunc/MAttNet>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RCCF

Accuracy: 65.73. Result ID: 698dae9e8b517eb4332318e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea22600.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea16023.md>)

Recorded evaluation configuration: {"Proposal-free":true,"Visual Extractor":"DLA-34"}. This record does not assert independent reproduction.

### DGA

Accuracy: 63.28. Result ID: 698dae9e8b517eb4332318e2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea22600.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66641e209131cea100d4.md>)

Recorded evaluation configuration: {"Proposal-free":false,"Visual Extractor":"VGG-16"}. This record does not assert independent reproduction.

### MCN

Accuracy: 62.29. Result ID: 698dae9e8b517eb4332318e5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea22600.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67361e209131cea14d7e.md>)

[Implementation](<https://github.com/luogen1996/MCN>)

Recorded evaluation configuration: {"Proposal-free":true,"Visual Extractor":"VGG-16"}. This record does not assert independent reproduction.

### SLR

Accuracy: 59.63. Result ID: 698dae9e8b517eb4332318e1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea22600.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634e1e209131ce9fdf7a.md>)

Recorded evaluation configuration: {"Proposal-free":false,"Visual Extractor":"ResNet-101"}. This record does not assert independent reproduction.

### FAOAVG

Accuracy: 57.45. Result ID: 698dae9e8b517eb4332318e4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa697c1e209131cea22600.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66351e209131cea0ec75.md>)

Recorded evaluation configuration: {"Proposal-free":true,"Visual Extractor":"DarkNet-53"}. This record does not assert independent reproduction.

### Phi-3-Vision-4B

Accuracy: 37.6. Result ID: 699370673a6c31484915efc2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65504.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74ae1e209131cea632e1.md>)

Recorded evaluation configuration: {"Model Size Category":"3B"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
