# Fine-Grained Visual Understanding on MMStar

Source: [Fine-Grained Visual Understanding on MMStar](<https://www.sota2.com/research/sota/fine-grained-visual-understanding-on-mmstar>)

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

Data updated: 2026-06-09T07:03:02.063Z

Evaluation of model performance on the MMStar dataset, specifically focusing on fine-grained visual understanding capabilities.

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 | fine-grained visual understanding |
| Dataset (including any stated split) | MMStar |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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/fine-grained-visual-understanding-on-mmstar.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/fine-grained-visual-understanding-on-mmstar.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MMS-PRM | 65.2 | Not recorded | 6a279de790966ade919bf54c |
| LLaVA-OneVision | 61.7 | Not recorded | 6a279de790966ade919bf54c |
| Insight-V | 61.5 | Not recorded | 6a279de790966ade919bf54c |
| Vision-R1-LlamaV | 61.4 | Not recorded | 6a279de790966ade919bf54c |
| InternVL2.5-MPO + SFT | 61 | Not recorded | 6a279de790966ade919bf54c |
| Qwen2-VL | 60.7 | Not recorded | 6a279de790966ade919bf54c |
| InternVL2.5-MPO | 60.7 | Not recorded | 6a279de790966ade919bf54c |
| R1-VL | 60 | Not recorded | 6a279de790966ade919bf54c |
| IXC-2.5 | 59.9 | Not recorded | 6a279de790966ade919bf54c |
| InternVL-2.5 | 59.6 | Not recorded | 6a279de790966ade919bf54c |
| LlamaV-o1 | 59.5 | Not recorded | 6a279de790966ade919bf54c |
| LLaVA-CoT | 57.6 | Not recorded | 6a279de790966ade919bf54c |
| MiniCPM-V-2-6 | 57.5 | Not recorded | 6a279de790966ade919bf54c |
| Ovis1.5-LLaMA3 | 57.3 | Not recorded | 6a279de790966ade919bf54c |
| LLaVA-NeXT-LLaMA3 + SFT | 54.7 | Not recorded | 6a279de790966ade919bf54c |
| LLaVA-NeXT-LLaMA3 | 43.1 | Not recorded | 6a279de790966ade919bf54c |
| LLaVA-1.5 | 32.8 | Not recorded | 6a279de790966ade919bf54c |

### MMS-PRM

Accuracy: 65.2. Result ID: 6a27ba6ffbc373592c23f9de.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

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

### LLaVA-OneVision

Accuracy: 61.7. Result ID: 6a27ba6ffbc373592c23f9d6.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e58.md>)

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

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

### Insight-V

Accuracy: 61.5. Result ID: 6a27ba6ffbc373592c23f9d8.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78541e209131cea77be2.md>)

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

### Vision-R1-LlamaV

Accuracy: 61.4. Result ID: 6a27ba6ffbc373592c23f9d3.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77591e209131cea72979.md>)

Recorded evaluation configuration: {"Size":"11B"}. This record does not assert independent reproduction.

### InternVL2.5-MPO + SFT

Accuracy: 61. Result ID: 6a27ba6ffbc373592c23f9dd.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77e01e209131cea75bd5.md>)

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

### Qwen2-VL

Accuracy: 60.7. Result ID: 6a27ba6ffbc373592c23f9d7.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75151e209131cea65976.md>)

[Implementation](<https://github.com/QwenLM/Qwen2-VL>)

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

### InternVL2.5-MPO

Accuracy: 60.7. Result ID: 6a27ba6ffbc373592c23f9dc.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77e01e209131cea75bd5.md>)

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

### R1-VL

Accuracy: 60. Result ID: 6a27ba6ffbc373592c23f9d4.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a651e209131cea82e9b.md>)

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

### IXC-2.5

Accuracy: 59.9. Result ID: 6a27ba6ffbc373592c23f9cf.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74021e209131cea5f31a.md>)

[Implementation](<https://github.com/InternLM/InternLM-XComposer>)

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

### InternVL-2.5

Accuracy: 59.6. Result ID: 6a27ba6ffbc373592c23f9d9.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bab1e209131cea89c7f.md>)

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

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

### LlamaV-o1

Accuracy: 59.5. Result ID: 6a27ba6ffbc373592c23f9d2.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76881e209131cea6d7bc.md>)

Recorded evaluation configuration: {"Size":"11B"}. This record does not assert independent reproduction.

### LLaVA-CoT

Accuracy: 57.6. Result ID: 6a27ba6ffbc373592c23f9d1.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a1b1e209131cea81353.md>)

Recorded evaluation configuration: {"Size":"11B"}. This record does not assert independent reproduction.

### MiniCPM-V-2-6

Accuracy: 57.5. Result ID: 6a27ba6ffbc373592c23f9d5.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74681e209131cea6183d.md>)

[Implementation](<https://github.com/OpenBMB/MiniCPM-V>)

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

### Ovis1.5-LLaMA3

Accuracy: 57.3. Result ID: 6a27ba6ffbc373592c23f9d0.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73b21e209131cea5dfaa.md>)

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

### LLaVA-NeXT-LLaMA3 + SFT

Accuracy: 54.7. Result ID: 6a27ba6ffbc373592c23f9db.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

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

### LLaVA-NeXT-LLaMA3

Accuracy: 43.1. Result ID: 6a27ba6ffbc373592c23f9da.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

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

### LLaVA-1.5

Accuracy: 32.8. Result ID: 6a27ba6ffbc373592c23f9ce.

[Reporting paper](<https://www.sota2.com/research/paper/6a279de790966ade919bf54c.md>)

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

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

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

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