# Comprehensive Multimodal Evaluation on Multimodal Evaluation Suite Composite

Source: [Comprehensive Multimodal Evaluation on Multimodal Evaluation Suite Composite](<https://www.sota2.com/research/sota/comprehensive-multimodal-evaluation-on-multimodal-evaluation-suite-composite>)

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

Data updated: 2026-04-21T13:17:49.024Z

Evaluation summarizing performance across various multimodal capabilities using the Composite suite, reporting an overall 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 | Comprehensive Multimodal Evaluation |
| Dataset (including any stated split) | Multimodal Evaluation Suite Composite |
| Metric | Overall Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Overall Score](<https://www.sota2.com/research/sota/comprehensive-multimodal-evaluation-on-multimodal-evaluation-suite-composite.md?metric=Overall%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Overall Score | Result date | Report paper |
| --- | --- | --- | --- |
| EVE (Ours-8B-iter4) | 68.7 | Not recorded | 69e705217d0172140ec7f2bd |
| VisPlay-8B-iter3 | 67.7 | Not recorded | 69e705217d0172140ec7f2bd |
| Jigsaw-R1-8B | 67.5 | Not recorded | 69e705217d0172140ec7f2bd |
| MM-Zero-8B-iter3 | 66.7 | Not recorded | 69e705217d0172140ec7f2bd |
| Qwen3-VL-8B-Instruct | 66.5 | Not recorded | 69e705217d0172140ec7f2bd |

### EVE (Ours-8B-iter4)

Overall Score: 68.7. Result ID: 69e778e547f34ce924cf554f.

[Reporting paper](<https://www.sota2.com/research/paper/69e705217d0172140ec7f2bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e705217d0172140ec7f2bd.md>)

Recorded evaluation configuration: {"Model Category":"Pseudo-label-based Self-evolution Methods","Scale":"8B","Iteration":"4"}. This record does not assert independent reproduction.

### VisPlay-8B-iter3

Overall Score: 67.7. Result ID: 69e778e547f34ce924cf554d.

[Reporting paper](<https://www.sota2.com/research/paper/69e705217d0172140ec7f2bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691ea0bfd6b0dd334292e137.md>)

[Implementation](<https://github.com/bruno686/VisPlay>)

Recorded evaluation configuration: {"Model Category":"Pseudo-label-based Self-evolution Methods","Scale":"8B","Iteration":"3"}. This record does not assert independent reproduction.

### Jigsaw-R1-8B

Overall Score: 67.5. Result ID: 69e778e547f34ce924cf554c.

[Reporting paper](<https://www.sota2.com/research/paper/69e705217d0172140ec7f2bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c0e1e209131cea8c29c.md>)

Recorded evaluation configuration: {"Model Category":"Template-based Self-evolution Methods","Scale":"8B"}. This record does not assert independent reproduction.

### MM-Zero-8B-iter3

Overall Score: 66.7. Result ID: 69e778e547f34ce924cf554e.

[Reporting paper](<https://www.sota2.com/research/paper/69e705217d0172140ec7f2bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6fe2d603e6de3e45d12.md>)

[Implementation](<https://github.com/zli12321/MM-Zero>)

Recorded evaluation configuration: {"Model Category":"Pseudo-label-based Self-evolution Methods","Scale":"8B","Iteration":"3"}. This record does not assert independent reproduction.

### Qwen3-VL-8B-Instruct

Overall Score: 66.5. Result ID: 69e778e547f34ce924cf554b.

[Reporting paper](<https://www.sota2.com/research/paper/69e705217d0172140ec7f2bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Model Category":"Open-Source MLLMs","Scale":"8B"}. This record does not assert independent reproduction.

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