# Referring Expression Segmentation on RefCOCOm (val)

Source: [Referring Expression Segmentation on RefCOCOm (val)](<https://www.sota2.com/research/sota/referring-expression-segmentation-on-refcocom-val>)

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

Data updated: 2026-03-31T08:40:30.777Z

Evaluation of Referring Expression Segmentation performance on the validation split of the RefCOCOm dataset, specifically reporting Macro F1 score.

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 Segmentation |
| Dataset (including any stated split) | RefCOCOm (val) |
| Metric | Macro F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Macro F1](<https://www.sota2.com/research/sota/referring-expression-segmentation-on-refcocom-val.md?metric=Macro%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Macro F1 | Result date | Report paper |
| --- | --- | --- | --- |
| Moondream3-9B | 87.1 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| Falcon Perception | 77.3 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| Qwen3-VL-30B | 72.1 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| Qwen3-VL-8B | 64.7 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| Qwen3-VL-4B | 64.4 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| Moondream2-2B | 62 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| Qwen3-VL-2B | 54 | Not recorded | 69cb54fe0636e5bf4afc9e7c |
| SAM 3-0.9B | 36.4 | Not recorded | 69cb54fe0636e5bf4afc9e7c |

### Moondream3-9B

Macro F1: 87.1. Result ID: 69cb886b47f34ce924b3dcdb.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

Recorded evaluation configuration: {"Parameters":"9B"}. This record does not assert independent reproduction.

### Falcon Perception

Macro F1: 77.3. Result ID: 69cb886b47f34ce924b3dcdd.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

Recorded evaluation configuration: {"Parameters":"0.6B"}. This record does not assert independent reproduction.

### Qwen3-VL-30B

Macro F1: 72.1. Result ID: 69cb886b47f34ce924b3dcd9.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Parameters":"30B"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

Macro F1: 64.7. Result ID: 69cb886b47f34ce924b3dcd8.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction.

### Qwen3-VL-4B

Macro F1: 64.4. Result ID: 69cb886b47f34ce924b3dcd7.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction.

### Moondream2-2B

Macro F1: 62. Result ID: 69cb886b47f34ce924b3dcda.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

Recorded evaluation configuration: {"Parameters":"2B"}. This record does not assert independent reproduction.

### Qwen3-VL-2B

Macro F1: 54. Result ID: 69cb886b47f34ce924b3dcd6.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Parameters":"2B"}. This record does not assert independent reproduction.

### SAM 3-0.9B

Macro F1: 36.4. Result ID: 69cb886b47f34ce924b3dcdc.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54fe0636e5bf4afc9e7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6923e69bd6b0dd334292f0ad.md>)

[Implementation](<https://github.com/facebookresearch/sam3>)

Recorded evaluation configuration: {"Parameters":"0.9B"}. This record does not assert independent reproduction.

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