# Multi-choice Question Answering on M3GIA

Source: [Multi-choice Question Answering on M3GIA](<https://www.sota2.com/research/sota/multi-choice-question-answering-on-m3gia>)

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

Data updated: 2026-02-26T05:30:12.961Z

Evaluation of model performance on the M3GIA dataset for Multi-choice Question Answering, typically 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-choice Question Answering |
| Dataset (including any stated split) | M3GIA |
| Metric | Accuracy |
| Unit | PERCENT |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/multi-choice-question-answering-on-m3gia.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4o | 59.8 | Not recorded | 68fa766c1e209131cea6cdce |
| Qwen2 VL | 37.3 | Not recorded | 68fa766c1e209131cea6cdce |
| Baichuan-omni | 34.7 | Not recorded | 68fa766c1e209131cea6cdce |
| MiniCPM-Llama3-V 2.5 | 30.3 | Not recorded | 68fa766c1e209131cea6cdce |
| VITA | 27.7 | Not recorded | 68fa766c1e209131cea6cdce |

### GPT-4o

Accuracy: 59.8. Result ID: 69941f0a3a6c3148491b3245.

[Reporting paper](<https://www.sota2.com/research/paper/68fa766c1e209131cea6cdce.md>)

Recorded evaluation configuration: {"Model Modality Type":"Proprietary"}. This record does not assert independent reproduction.

### Qwen2 VL

Accuracy: 37.3. Result ID: 69941f0a3a6c3148491b3246.

[Reporting paper](<https://www.sota2.com/research/paper/68fa766c1e209131cea6cdce.md>)

Recorded evaluation configuration: {"Model Scale":"7B","Model Modality Type":"Vision-language"}. This record does not assert independent reproduction.

### Baichuan-omni

Accuracy: 34.7. Result ID: 69941f0a3a6c3148491b3249.

[Reporting paper](<https://www.sota2.com/research/paper/68fa766c1e209131cea6cdce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa766c1e209131cea6cdce.md>)

[Implementation](<https://github.com/westlake-baichuan-mllm/ocean-omni>)

Recorded evaluation configuration: {"Model Scale":"7B","Model Modality Type":"Omni-modal"}. This record does not assert independent reproduction.

### MiniCPM-Llama3-V 2.5

Accuracy: 30.3. Result ID: 69941f0a3a6c3148491b3247.

[Reporting paper](<https://www.sota2.com/research/paper/68fa766c1e209131cea6cdce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74681e209131cea6183d.md>)

[Implementation](<https://github.com/OpenBMB/MiniCPM-V>)

Recorded evaluation configuration: {"Model Scale":"8B","Model Modality Type":"Vision-language"}. This record does not assert independent reproduction.

### VITA

Accuracy: 27.7. Result ID: 69941f0a3a6c3148491b3248.

[Reporting paper](<https://www.sota2.com/research/paper/68fa766c1e209131cea6cdce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb11.md>)

Recorded evaluation configuration: {"Model Scale":"8x7B","Model Modality Type":"Omni-modal"}. This record does not assert independent reproduction.

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