# Multi-modal Understanding on CV-Bench, BLINK, RealWorldQA, MathVista, MMStar, MMVet Suite

Source: [Multi-modal Understanding on CV-Bench, BLINK, RealWorldQA, MathVista, MMStar, MMVet Suite](<https://www.sota2.com/research/sota/multi-modal-understanding-on-cv-bench-blink-realworldqa-mathvista-mmstar-mmvet-suite>)

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

Data updated: 2026-02-26T05:35:47.203Z

Aggregate evaluation covering multimodal understanding capabilities across CV-Bench, BLINK, RealWorldQA, MathVista, MMStar, and MMVet.

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 | Multi-modal Understanding |
| Dataset (including any stated split) | CV-Bench, BLINK, RealWorldQA, MathVista, MMStar, MMVet |
| Metric | Average Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Average Score](<https://www.sota2.com/research/sota/multi-modal-understanding-on-cv-bench-blink-realworldqa-mathvista-mmstar-mmvet-suite.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average Score | Result date | Report paper |
| --- | --- | --- | --- |
| LATTE | 53.8 | Not recorded | 68fa7b451e209131cea876c2 |
| Vanilla IT | 49.5 | Not recorded | 68fa7b451e209131cea876c2 |
| LATTE | 48.2 | Not recorded | 68fa7b451e209131cea876c2 |
| LATTE | 47.2 | Not recorded | 68fa7b451e209131cea876c2 |
| LATTE | 46.7 | Not recorded | 68fa7b451e209131cea876c2 |
| Vanilla IT | 43.1 | Not recorded | 68fa7b451e209131cea876c2 |
| Vanilla IT | 42.1 | Not recorded | 68fa7b451e209131cea876c2 |
| Vanilla IT | 41.6 | Not recorded | 68fa7b451e209131cea876c2 |

### LATTE

Average Score: 53.8. Result ID: 698b83e17a967eddb76f3b4e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Implementation](<https://github.com/SalesforceAIResearch/LATTE>)

Recorded evaluation configuration: {"Language / Vision":"Qwen2-7B/SigLIP","Starting checkpoint":"LLaVA-OV Stage 1.5"}. This record does not assert independent reproduction.

### Vanilla IT

Average Score: 49.5. Result ID: 698b83e17a967eddb76f3b4d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

Recorded evaluation configuration: {"Language / Vision":"Qwen2-7B/SigLIP","Starting checkpoint":"LLaVA-OV Stage 1.5"}. This record does not assert independent reproduction.

### LATTE

Average Score: 48.2. Result ID: 698b83e17a967eddb76f3b4c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Implementation](<https://github.com/SalesforceAIResearch/LATTE>)

Recorded evaluation configuration: {"Language / Vision":"LLaMA3-8B/SigLIP","Starting checkpoint":"Mantis Instruct-tuned"}. This record does not assert independent reproduction.

### LATTE

Average Score: 47.2. Result ID: 698b83e17a967eddb76f3b4a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Implementation](<https://github.com/SalesforceAIResearch/LATTE>)

Recorded evaluation configuration: {"Language / Vision":"LLaMA3-8B/CLIP","Starting checkpoint":"Mantis Pretrained (Configuration 2)"}. This record does not assert independent reproduction.

### LATTE

Average Score: 46.7. Result ID: 698b83e17a967eddb76f3b48.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

[Implementation](<https://github.com/SalesforceAIResearch/LATTE>)

Recorded evaluation configuration: {"Language / Vision":"LLaMA3-8B/CLIP","Starting checkpoint":"Mantis Pretrained"}. This record does not assert independent reproduction.

### Vanilla IT

Average Score: 43.1. Result ID: 698b83e17a967eddb76f3b4b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

Recorded evaluation configuration: {"Language / Vision":"LLaMA3-8B/SigLIP","Starting checkpoint":"Mantis Instruct-tuned"}. This record does not assert independent reproduction.

### Vanilla IT

Average Score: 42.1. Result ID: 698b83e17a967eddb76f3b49.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

Recorded evaluation configuration: {"Language / Vision":"LLaMA3-8B/CLIP","Starting checkpoint":"Mantis Pretrained (Configuration 2)"}. This record does not assert independent reproduction.

### Vanilla IT

Average Score: 41.6. Result ID: 698b83e17a967eddb76f3b47.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b451e209131cea876c2.md>)

Recorded evaluation configuration: {"Language / Vision":"LLaMA3-8B/CLIP","Starting checkpoint":"Mantis Pretrained"}. This record does not assert independent reproduction.

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