# General Multimodal Understanding on MUIR

Source: [General Multimodal Understanding on MUIR](<https://www.sota2.com/research/sota/general-multimodal-understanding-on-muir>)

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

Data updated: 2026-03-25T15:37:19.285Z

Evaluation of model performance on the MUIR dataset focusing on General Multimodal Understanding capabilities, 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 | General Multimodal Understanding |
| Dataset (including any stated split) | MUIR |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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/general-multimodal-understanding-on-muir.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3-VL-30B-CoT | 77.6 | Not recorded | 69a66bc62d603e6de3e3cb29 |
| GPT-5 | 77.5 | Not recorded | 69a66bc62d603e6de3e3cb29 |
| Gemini-2.5-Pro | 77.2 | Not recorded | 69a66bc62d603e6de3e3cb29 |
| Qwen3-VL-4B-CoT | 73.8 | Not recorded | 69a66bc62d603e6de3e3cb29 |
| ReMoT-4b-CoT | 72.8 | Not recorded | 69a66bc62d603e6de3e3cb29 |
| GPT-4o | 68 | Not recorded | 69a66bc62d603e6de3e3cb29 |
| Qwen2.5-VL-7B | 59.6 | Not recorded | 69a66bc62d603e6de3e3cb29 |
| InternVL2.5-8B | 55 | Not recorded | 69a66bc62d603e6de3e3cb29 |
| VISOR | 28.1 | Not recorded | 69c36c2c0636e5bf4afc6619 |
| LLaVA | 26.8 | Not recorded | 69c36c2c0636e5bf4afc6619 |

### Qwen3-VL-30B-CoT

Accuracy: 77.6. Result ID: 69a7fdfb6dbb7075b94d33af.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bc62d603e6de3e3cb29.md>)

Recorded evaluation configuration: {"Model Size":"30B","Thinking Mode":"CoT"}. This record does not assert independent reproduction.

### GPT-5

Accuracy: 77.5. Result ID: 69a7fdfb6dbb7075b94d33ab.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bc62d603e6de3e3cb29.md>)

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

### Gemini-2.5-Pro

Accuracy: 77.2. Result ID: 69a7fdfb6dbb7075b94d33a9.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bc62d603e6de3e3cb29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c311e209131cea8cef5.md>)

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

### Qwen3-VL-4B-CoT

Accuracy: 73.8. Result ID: 69a7fdfb6dbb7075b94d33ae.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bc62d603e6de3e3cb29.md>)

Recorded evaluation configuration: {"Model Size":"4B","Thinking Mode":"CoT"}. This record does not assert independent reproduction.

### ReMoT-4b-CoT

Accuracy: 72.8. Result ID: 69a7fdfb6dbb7075b94d33b0.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bc62d603e6de3e3cb29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66bc62d603e6de3e3cb29.md>)

Recorded evaluation configuration: {"Model Size":"4b","Thinking Mode":"CoT"}. This record does not assert independent reproduction.

### GPT-4o

Accuracy: 68. Result ID: 69a7fdfb6dbb7075b94d33aa.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bc62d603e6de3e3cb29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75681e209131cea67a98.md>)

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

### Qwen2.5-VL-7B

Accuracy: 59.6. Result ID: 69a7fdfb6dbb7075b94d33ac.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bc62d603e6de3e3cb29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

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

### InternVL2.5-8B

Accuracy: 55. Result ID: 69a7fdfb6dbb7075b94d33ad.

[Reporting paper](<https://www.sota2.com/research/paper/69a66bc62d603e6de3e3cb29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

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

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

### VISOR

Accuracy: 28.1. Result ID: 69c4011e47f34ce924ae4075.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c2c0636e5bf4afc6619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c36c2c0636e5bf4afc6619.md>)

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

### LLaVA

Accuracy: 26.8. Result ID: 69c4011e47f34ce924ae4074.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c2c0636e5bf4afc6619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa732e1e209131cea5af59.md>)

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

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

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