# Embodied Pointing & Location on PointBench (test)

Source: [Embodied Pointing & Location on PointBench (test)](<https://www.sota2.com/research/sota/embodied-pointing-and-location-on-pointbench-test>)

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

Data updated: 2026-06-11T09:26:04.055Z

Evaluation of model performance on the Embodied Pointing & Location task using the test split of the PointBench dataset, measured by 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 | Embodied Pointing & Location |
| Dataset (including any stated split) | PointBench (test) |
| Metric | Accuracy (%) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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/embodied-pointing-and-location-on-pointbench-test.md?metric=Accuracy%20(%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (%) | Result date | Report paper |
| --- | --- | --- | --- |
| Embodied-R1.5 | 74.6 | Not recorded | 6a2a40eed33dfb23e78391ab |
| Gemini-Robotics-ER-1.5 | 70.7 | Not recorded | 6a2a40eed33dfb23e78391ab |
| Qwen3-VL-8B | 65.6 | Not recorded | 6a2a40eed33dfb23e78391ab |
| Gemini-2.5-Pro | 62.8 | Not recorded | 6a2a40eed33dfb23e78391ab |
| Molmo-D-7B | 61.6 | Not recorded | 6a2a40eed33dfb23e78391ab |
| RoboBrain-2.0-7B | 60.4 | Not recorded | 6a2a40eed33dfb23e78391ab |
| Mimo-Embodied | 50.2 | Not recorded | 6a2a40eed33dfb23e78391ab |
| Embodied-R1 | 49.7 | Not recorded | 6a2a40eed33dfb23e78391ab |
| GPT-5.4 | 37.9 | Not recorded | 6a2a40eed33dfb23e78391ab |
| Pelican-VL-1.0 | 36.4 | Not recorded | 6a2a40eed33dfb23e78391ab |
| InternVL3.5-8B | 32.4 | Not recorded | 6a2a40eed33dfb23e78391ab |
| GPT-4o | 29.5 | Not recorded | 6a2a40eed33dfb23e78391ab |
| Magma | 23.4 | Not recorded | 6a2a40eed33dfb23e78391ab |
| VeBrain | 20.2 | Not recorded | 6a2a40eed33dfb23e78391ab |

### Embodied-R1.5

Accuracy (%): 74.6. Result ID: 6a2a7e8afbc373592c27edbc.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

[Implementation](<https://github.com/pickxiguapi/Embodied-R1.5>)

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

### Gemini-Robotics-ER-1.5

Accuracy (%): 70.7. Result ID: 6a2a7e8afbc373592c27edb5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a21e209131cea747ed.md>)

Recorded evaluation configuration: {"Category":"Embodied VLM","Version":"ER-1.5"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

Accuracy (%): 65.6. Result ID: 6a2a7e8afbc373592c27edb2.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

Recorded evaluation configuration: {"Category":"General-Purpose VLM","Parameters":"8B"}. This record does not assert independent reproduction.

### Gemini-2.5-Pro

Accuracy (%): 62.8. Result ID: 6a2a7e8afbc373592c27edb1.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

Recorded evaluation configuration: {"Category":"General-Purpose VLM"}. This record does not assert independent reproduction.

### Molmo-D-7B

Accuracy (%): 61.6. Result ID: 6a2a7e8afbc373592c27edb4.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76101e209131cea6b37c.md>)

[Implementation](<https://molmo.allenai.org/>)

Recorded evaluation configuration: {"Category":"General-Purpose VLM","Parameters":"7B"}. This record does not assert independent reproduction.

### RoboBrain-2.0-7B

Accuracy (%): 60.4. Result ID: 6a2a7e8afbc373592c27edb6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77931e209131cea74136.md>)

Recorded evaluation configuration: {"Category":"Embodied VLM","Parameters":"7B"}. This record does not assert independent reproduction.

### Mimo-Embodied

Accuracy (%): 50.2. Result ID: 6a2a7e8afbc373592c27edb8.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691ff204d6b0dd334292e641.md>)

[Implementation](<https://github.com/XiaomiMiMo/MiMo-Embodied>)

Recorded evaluation configuration: {"Category":"Embodied VLM"}. This record does not assert independent reproduction.

### Embodied-R1

Accuracy (%): 49.7. Result ID: 6a2a7e8afbc373592c27edbb.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

Recorded evaluation configuration: {"Category":"Embodied VLM"}. This record does not assert independent reproduction.

### GPT-5.4

Accuracy (%): 37.9. Result ID: 6a2a7e8afbc373592c27edb0.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

Recorded evaluation configuration: {"Category":"General-Purpose VLM"}. This record does not assert independent reproduction.

### Pelican-VL-1.0

Accuracy (%): 36.4. Result ID: 6a2a7e8afbc373592c27edb9.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988753ef7ccd74e5e5a1d.md>)

Recorded evaluation configuration: {"Category":"Embodied VLM","Version":"1.0"}. This record does not assert independent reproduction.

### InternVL3.5-8B

Accuracy (%): 32.4. Result ID: 6a2a7e8afbc373592c27edb3.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85dc9.md>)

Recorded evaluation configuration: {"Category":"General-Purpose VLM","Parameters":"8B"}. This record does not assert independent reproduction.

### GPT-4o

Accuracy (%): 29.5. Result ID: 6a2a7e8afbc373592c27edaf.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

Recorded evaluation configuration: {"Category":"General-Purpose VLM"}. This record does not assert independent reproduction.

### Magma

Accuracy (%): 23.4. Result ID: 6a2a7e8afbc373592c27edba.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770b1e209131cea70b91.md>)

[Implementation](<https://microsoft.github.io/Magma>)

Recorded evaluation configuration: {"Category":"Embodied VLM"}. This record does not assert independent reproduction.

### VeBrain

Accuracy (%): 20.2. Result ID: 6a2a7e8afbc373592c27edb7.

[Reporting paper](<https://www.sota2.com/research/paper/6a2a40eed33dfb23e78391ab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78fa1e209131cea7b711.md>)

Recorded evaluation configuration: {"Category":"Embodied VLM"}. This record does not assert independent reproduction.

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