# Visual Question Answering on Mantis

Source: [Visual Question Answering on Mantis](<https://www.sota2.com/research/sota/visual-question-answering-on-mantis>)

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

Data updated: 2026-04-29T07:43:14.566Z

Evaluation of model performance on the Mantis dataset for Visual Question Answering, typically measured using Accuracy.

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 | Visual Question Answering |
| Dataset (including any stated split) | Mantis |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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/visual-question-answering-on-mantis.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MiMo-VL | 81.57 | Not recorded | 691ff204d6b0dd334292e641 |
| MiMo-Embodied | 81.1 | Not recorded | 691ff204d6b0dd334292e641 |
| GPT-4o | 75.6 | Not recorded | 691ff204d6b0dd334292e641 |
| Claude 3.7 Sonnet | 75.1 | Not recorded | 691ff204d6b0dd334292e641 |
| Qwen2.5-VL | 74.7 | Not recorded | 691ff204d6b0dd334292e641 |
| InternVL3 | 72.8 | Not recorded | 691ff204d6b0dd334292e641 |

### MiMo-VL

Accuracy: 81.57. Result ID: 69f1b67e47f34ce924d7e992.

[Reporting paper](<https://www.sota2.com/research/paper/691ff204d6b0dd334292e641.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79121e209131cea7bfbd.md>)

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

### MiMo-Embodied

Accuracy: 81.1. Result ID: 69f1b67e47f34ce924d7e997.

[Reporting paper](<https://www.sota2.com/research/paper/691ff204d6b0dd334292e641.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691ff204d6b0dd334292e641.md>)

[Implementation](<https://github.com/XiaomiMiMo/MiMo-Embodied>)

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

### GPT-4o

Accuracy: 75.6. Result ID: 69f1b67e47f34ce924d7e995.

[Reporting paper](<https://www.sota2.com/research/paper/691ff204d6b0dd334292e641.md>)

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

Recorded evaluation configuration: {"Params":"–"}. This record does not assert independent reproduction.

### Claude 3.7 Sonnet

Accuracy: 75.1. Result ID: 69f1b67e47f34ce924d7e996.

[Reporting paper](<https://www.sota2.com/research/paper/691ff204d6b0dd334292e641.md>)

Recorded evaluation configuration: {"Params":"–"}. This record does not assert independent reproduction.

### Qwen2.5-VL

Accuracy: 74.7. Result ID: 69f1b67e47f34ce924d7e993.

[Reporting paper](<https://www.sota2.com/research/paper/691ff204d6b0dd334292e641.md>)

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

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

### InternVL3

Accuracy: 72.8. Result ID: 69f1b67e47f34ce924d7e994.

[Reporting paper](<https://www.sota2.com/research/paper/691ff204d6b0dd334292e641.md>)

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

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

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