# Multimodal News Classification on NewsMM (test)

Source: [Multimodal News Classification on NewsMM (test)](<https://www.sota2.com/research/sota/multimodal-news-classification-on-newsmm-test>)

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

Data updated: 2026-04-07T08:08:21.608Z

Evaluation of Multimodal News Classification performance on the test split of the NewsMM dataset, using Accuracy, Macro Precision, Macro Recall, and Macro F1 scores.

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 News Classification |
| Dataset (including any stated split) | NewsMM (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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/multimodal-news-classification-on-newsmm-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Macro Precision](<https://www.sota2.com/research/sota/multimodal-news-classification-on-newsmm-test.md?metric=Macro%20Precision>): Higher is better; unit: PERCENT.

- [Macro Recall](<https://www.sota2.com/research/sota/multimodal-news-classification-on-newsmm-test.md?metric=Macro%20Recall>): Higher is better; unit: PERCENT.

- [Macro F1](<https://www.sota2.com/research/sota/multimodal-news-classification-on-newsmm-test.md?metric=Macro%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MultiPress | 91.2 | Not recorded | 69d48f5e7d0172140ec74110 |
| MultiPress | 85.3 | Not recorded | 69d48f5e7d0172140ec74110 |
| Qwen2.5-VL-7B | 80.2 | Not recorded | 69d48f5e7d0172140ec74110 |
| GPT-4o-20250513 | 79.6 | Not recorded | 69d48f5e7d0172140ec74110 |
| Qwen2.5-VL-7B | 77.4 | Not recorded | 69d48f5e7d0172140ec74110 |
| GLM-4V-9B | 70.5 | Not recorded | 69d48f5e7d0172140ec74110 |
| mPLUG-7B | 68.9 | Not recorded | 69d48f5e7d0172140ec74110 |
| Qwen2.5-VL-3B | 66.8 | Not recorded | 69d48f5e7d0172140ec74110 |
| Qwen2.5-VL-3B | 62.3 | Not recorded | 69d48f5e7d0172140ec74110 |

### MultiPress

Accuracy: 91.2. Result ID: 69d4bb5847f34ce924bc6450.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f5e7d0172140ec74110.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d48f5e7d0172140ec74110.md>)

Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction.

### MultiPress

Accuracy: 85.3. Result ID: 69d4bb5847f34ce924bc6451.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f5e7d0172140ec74110.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d48f5e7d0172140ec74110.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Accuracy: 80.2. Result ID: 69d4bb5847f34ce924bc644e.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f5e7d0172140ec74110.md>)

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

Recorded evaluation configuration: {"Evaluation Protocol":"fine-tuned"}. This record does not assert independent reproduction.

### GPT-4o-20250513

Accuracy: 79.6. Result ID: 69d4bb5847f34ce924bc644f.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f5e7d0172140ec74110.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: 77.4. Result ID: 69d4bb5847f34ce924bc644d.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f5e7d0172140ec74110.md>)

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

Recorded evaluation configuration: {"Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

### GLM-4V-9B

Accuracy: 70.5. Result ID: 69d4bb5847f34ce924bc6449.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f5e7d0172140ec74110.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74521e209131cea610b6.md>)

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

### mPLUG-7B

Accuracy: 68.9. Result ID: 69d4bb5847f34ce924bc644a.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f5e7d0172140ec74110.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ae1e209131cea57d83.md>)

[Implementation](<https://github.com/X-PLUG/mPLUG-Owl>)

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

### Qwen2.5-VL-3B

Accuracy: 66.8. Result ID: 69d4bb5847f34ce924bc644c.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f5e7d0172140ec74110.md>)

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

Recorded evaluation configuration: {"Evaluation Protocol":"fine-tuned"}. This record does not assert independent reproduction.

### Qwen2.5-VL-3B

Accuracy: 62.3. Result ID: 69d4bb5847f34ce924bc644b.

[Reporting paper](<https://www.sota2.com/research/paper/69d48f5e7d0172140ec74110.md>)

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

Recorded evaluation configuration: {"Evaluation Protocol":"zero-shot"}. This record does not assert independent reproduction.

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