# Multi-modal Visual Question Answering on VQA-T

Source: [Multi-modal Visual Question Answering on VQA-T](<https://www.sota2.com/research/sota/multi-modal-visual-question-answering-on-vqa-t>)

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

Data updated: 2026-02-26T05:30:34.231Z

Evaluation of model performance on the VQA-T dataset for Multi-modal Visual Question Answering, measured by 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 | Multi-modal Visual Question Answering |
| Dataset (including any stated split) | VQA-T |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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/multi-modal-visual-question-answering-on-vqa-t.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| 16-bit Baseline | 64.84 | Not recorded | 68fa78f21e209131cea7b600 |
| AMXFP4 | 59.13 | Not recorded | 68fa78f21e209131cea7b600 |
| MXFP4 | 57.88 | Not recorded | 68fa78f21e209131cea7b600 |
| MXFP4-PoT | 50.05 | Not recorded | 68fa78f21e209131cea7b600 |

### 16-bit Baseline

Accuracy: 64.84. Result ID: 6995b2293badfaffe6b1f110.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b600.md>)

Recorded evaluation configuration: {"Data Format":"16-bit","Backbone":"LLaVA1.6-7B"}. This record does not assert independent reproduction.

### AMXFP4

Accuracy: 59.13. Result ID: 6995b2293badfaffe6b1f113.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b600.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b600.md>)

[Implementation](<https://www.sota2.com/aiha-lab/MX-QLLM.git>)

Recorded evaluation configuration: {"Data Format":"AMXFP4","Backbone":"LLaVA1.6-7B"}. This record does not assert independent reproduction.

### MXFP4

Accuracy: 57.88. Result ID: 6995b2293badfaffe6b1f112.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b600.md>)

Recorded evaluation configuration: {"Data Format":"MXFP4","Backbone":"LLaVA1.6-7B"}. This record does not assert independent reproduction.

### MXFP4-PoT

Accuracy: 50.05. Result ID: 6995b2293badfaffe6b1f111.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78f21e209131cea7b600.md>)

Recorded evaluation configuration: {"Data Format":"MXFP4-PoT","Backbone":"LLaVA1.6-7B"}. This record does not assert independent reproduction.

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