# Multimodal Reasoning Accuracy on MM-Vet

Source: [Multimodal Reasoning Accuracy on MM-Vet](<https://www.sota2.com/research/sota/multimodal-reasoning-accuracy-on-mm-vet>)

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

Data updated: 2026-04-14T08:49:41.949Z

Evaluation of model performance on the MM-Vet benchmark specifically reporting the overall accuracy 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 | Multimodal Reasoning |
| Dataset (including any stated split) | MM-Vet |
| Metric | Pass@1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 24 of 24 |
| 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

- [Pass@1 Accuracy](<https://www.sota2.com/research/sota/multimodal-reasoning-accuracy-on-mm-vet.md?metric=Pass%401%20Accuracy>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/multimodal-reasoning-accuracy-on-mm-vet.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| InternVL3-9B | 76.2 | Not recorded | 69ddca347d0172140ec79b4e |
| Qwen2.5-VL-7B-Instruct + RFT | 73.8 | Not recorded | 69ddca347d0172140ec79b4e |
| Claude-3.5-Sonnet | 70.1 | Not recorded | 69ddca347d0172140ec79b4e |
| GPT-4o-20240513 | 69.1 | Not recorded | 69ddca347d0172140ec79b4e |
| GPT-4V | 67.5 | Not recorded | 69ddca347d0172140ec79b4e |
| Qwen2.5-VL-7B-Instruct | 67.2 | Not recorded | 69ddca347d0172140ec79b4e |
| Qwen2.5-VL-7B-Instruct | 67.1 | Not recorded | 69ddca347d0172140ec79b4e |
| Qwen2.5-VL-7B-Instruct | 67.1 | Not recorded | 69ddca347d0172140ec79b4e |
| InternVL2.5-26B | 65 | Not recorded | 69ddca347d0172140ec79b4e |
| Qwen2.5-VL-7B-Instruct + cold start | 64.2 | Not recorded | 69ddca347d0172140ec79b4e |
| Gemini-1.5-Pro | 64 | Not recorded | 69ddca347d0172140ec79b4e |
| InternVL2.5-8B | 62.8 | Not recorded | 69ddca347d0172140ec79b4e |
| Qwen2-VL-7B | 62 | Not recorded | 69ddca347d0172140ec79b4e |
| LLaVA-OneVision-72B | 60.6 | Not recorded | 69ddca347d0172140ec79b4e |
| MiniCPM-V2.6 | 60 | Not recorded | 69ddca347d0172140ec79b4e |
| Cambrian-34B | 53.2 | Not recorded | 69ddca347d0172140ec79b4e |

### InternVL3-9B

Pass@1 Accuracy: 76.2. Result ID: 69ddffa047f34ce924c582b3.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fa5.md>)

Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B-Instruct + RFT

Pass@1 Accuracy: 73.8. Result ID: 69ddffa047f34ce924c582bc.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

Recorded evaluation configuration: {"Model Source Category":"Ours","Training Strategy":"RFT"}. This record does not assert independent reproduction.

### Claude-3.5-Sonnet

Pass@1 Accuracy: 70.1. Result ID: 69ddffa047f34ce924c582af.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

Recorded evaluation configuration: {"Model Source Category":"Closed-Source Models"}. This record does not assert independent reproduction.

### GPT-4o-20240513

Pass@1 Accuracy: 69.1. Result ID: 69ddffa047f34ce924c582ae.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

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

Recorded evaluation configuration: {"Model Source Category":"Closed-Source Models"}. This record does not assert independent reproduction.

### GPT-4V

Pass@1 Accuracy: 67.5. Result ID: 69ddffa047f34ce924c582ad.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

Recorded evaluation configuration: {"Model Source Category":"Closed-Source Models"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B-Instruct

Pass@1 Accuracy: 67.2. Result ID: 69ddffa047f34ce924c582b9.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

Recorded evaluation configuration: {"Model Source Category":"Base Model","Chain-of-Thought (CoT)":"true"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B-Instruct

Pass@1 Accuracy: 67.1. Result ID: 69ddffa047f34ce924c582b8.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

Recorded evaluation configuration: {"Model Source Category":"Base Model"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B-Instruct

Pass@1 Accuracy: 67.1. Result ID: 69ddffa047f34ce924c582ba.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

Recorded evaluation configuration: {"Model Source Category":"Ours"}. This record does not assert independent reproduction.

### InternVL2.5-26B

Pass@1 Accuracy: 65. Result ID: 69ddffa047f34ce924c582b7.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

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

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

Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B-Instruct + cold start

Pass@1 Accuracy: 64.2. Result ID: 69ddffa047f34ce924c582bb.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

Recorded evaluation configuration: {"Model Source Category":"Ours","Training Strategy":"cold start"}. This record does not assert independent reproduction.

### Gemini-1.5-Pro

Pass@1 Accuracy: 64. Result ID: 69ddffa047f34ce924c582b0.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

Recorded evaluation configuration: {"Model Source Category":"Closed-Source Models"}. This record does not assert independent reproduction.

### InternVL2.5-8B

Pass@1 Accuracy: 62.8. Result ID: 69ddffa047f34ce924c582b1.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

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

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

Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction.

### Qwen2-VL-7B

Pass@1 Accuracy: 62. Result ID: 69ddffa047f34ce924c582b4.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

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

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

Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction.

### LLaVA-OneVision-72B

Pass@1 Accuracy: 60.6. Result ID: 69ddffa047f34ce924c582b6.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

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

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

Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction.

### MiniCPM-V2.6

Pass@1 Accuracy: 60. Result ID: 69ddffa047f34ce924c582b2.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3ab.md>)

Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction.

### Cambrian-34B

Pass@1 Accuracy: 53.2. Result ID: 69ddffa047f34ce924c582b5.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75fa1e209131cea6ac2e.md>)

Recorded evaluation configuration: {"Model Source Category":"Open-Source Models"}. This record does not assert independent reproduction.

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