# 3D Visual Question Answering on MM-Vet

Source: [3D Visual Question Answering on MM-Vet](<https://www.sota2.com/research/sota/3d-visual-question-answering-on-mm-vet>)

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

Data updated: 2026-03-11T07:19:35.048Z

Evaluation of model performance on the MM-Vet dataset specifically for 3D Visual Question Answering tasks, typically measured using LLM-as-a-judge metrics.

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 | 3D Visual Question Answering |
| Dataset (including any stated split) | MM-Vet |
| Metric | GPT-4 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [GPT-4 Score](<https://www.sota2.com/research/sota/3d-visual-question-answering-on-mm-vet.md?metric=GPT-4%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | GPT-4 Score | Result date | Report paper |
| --- | --- | --- | --- |
| SAGE-13B | 54.89 | Not recorded | 69b0f6fc2d603e6de3e45cf1 |
| SAGE-13B\* | 53.21 | Not recorded | 69b0f6fc2d603e6de3e45cf1 |
| ShapeLLM-13B | 53.1 | Not recorded | 69b0f6fc2d603e6de3e45cf1 |
| SAGE-7B | 49.53 | Not recorded | 69b0f6fc2d603e6de3e45cf1 |
| LLaVA-13B | 47.9 | Not recorded | 69b0f6fc2d603e6de3e45cf1 |
| ShapeLLM-7B | 47.4 | Not recorded | 69b0f6fc2d603e6de3e45cf1 |
| PointLLM-13B | 46.6 | Not recorded | 69b0f6fc2d603e6de3e45cf1 |
| SAGE-7B\* | 46.38 | Not recorded | 69b0f6fc2d603e6de3e45cf1 |
| PointLLM-7B | 41.2 | Not recorded | 69b0f6fc2d603e6de3e45cf1 |

### SAGE-13B

GPT-4 Score: 54.89. Result ID: 69b117696dbb7075b95b114a.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

Recorded evaluation configuration: {"Model Scale":"13B","Preference Optimization":"true"}. This record does not assert independent reproduction.

### SAGE-13B\*

GPT-4 Score: 53.21. Result ID: 69b117696dbb7075b95b1149.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

Recorded evaluation configuration: {"Model Scale":"13B","Preference Optimization":"false"}. This record does not assert independent reproduction.

### ShapeLLM-13B

GPT-4 Score: 53.1. Result ID: 69b117696dbb7075b95b1146.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa740c1e209131cea5f73a.md>)

[Implementation](<https://qizekun.github.io/ShapeLLM>)

Recorded evaluation configuration: {"Model Scale":"13B"}. This record does not assert independent reproduction.

### SAGE-7B

GPT-4 Score: 49.53. Result ID: 69b117696dbb7075b95b1148.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

Recorded evaluation configuration: {"Model Scale":"7B","Preference Optimization":"true"}. This record does not assert independent reproduction.

### LLaVA-13B

GPT-4 Score: 47.9. Result ID: 69b117696dbb7075b95b1142.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Model Scale":"13B"}. This record does not assert independent reproduction.

### ShapeLLM-7B

GPT-4 Score: 47.4. Result ID: 69b117696dbb7075b95b1145.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa740c1e209131cea5f73a.md>)

[Implementation](<https://qizekun.github.io/ShapeLLM>)

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

### PointLLM-13B

GPT-4 Score: 46.6. Result ID: 69b117696dbb7075b95b1144.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b44.md>)

[Implementation](<https://github.com/OpenRobotLab/PointLLM>)

Recorded evaluation configuration: {"Model Scale":"13B"}. This record does not assert independent reproduction.

### SAGE-7B\*

GPT-4 Score: 46.38. Result ID: 69b117696dbb7075b95b1147.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

Recorded evaluation configuration: {"Model Scale":"7B","Preference Optimization":"false"}. This record does not assert independent reproduction.

### PointLLM-7B

GPT-4 Score: 41.2. Result ID: 69b117696dbb7075b95b1143.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6fc2d603e6de3e45cf1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b44.md>)

[Implementation](<https://github.com/OpenRobotLab/PointLLM>)

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

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