# Multimodal Fact-checking on MMA-Bench

Source: [Multimodal Fact-checking on MMA-Bench](<https://www.sota2.com/research/sota/multimodal-fact-checking-on-mma-bench>)

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

Data updated: 2026-02-26T05:39:52.254Z

Evaluation of model performance on the MMA-Bench dataset for Multimodal Fact-checking, utilizing metrics such as Core Accuracy, Verdict Accuracy, and CoRe 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 | Multimodal Fact-checking |
| Dataset (including any stated split) | MMA-Bench |
| Metric | Core 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

- [Core Accuracy](<https://www.sota2.com/research/sota/multimodal-fact-checking-on-mma-bench.md?metric=Core%20Accuracy>): Higher is better; unit: PERCENT.

- [Verdict Accuracy](<https://www.sota2.com/research/sota/multimodal-fact-checking-on-mma-bench.md?metric=Verdict%20Accuracy>): Higher is better; unit: PERCENT.

- [CoRe Score](<https://www.sota2.com/research/sota/multimodal-fact-checking-on-mma-bench.md?metric=CoRe%20Score>): Higher is better; unit: SCALAR.

- [Type B Accuracy](<https://www.sota2.com/research/sota/multimodal-fact-checking-on-mma-bench.md?metric=Type%20B%20Accuracy>): Higher is better; unit: PERCENT.

- [Type D Score](<https://www.sota2.com/research/sota/multimodal-fact-checking-on-mma-bench.md?metric=Type%20D%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Core Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MIRIX | 32.67 | Not recorded | 6996990909c33900fcd71efc |
| MIRIX | 30.94 | Not recorded | 6996990909c33900fcd71efc |
| MMA | 13.55 | Not recorded | 6996990909c33900fcd71efc |
| MMA | 13.15 | Not recorded | 6996990909c33900fcd71efc |

### MIRIX

Core Accuracy: 32.67. Result ID: 699af1965698665ec482b61c.

[Reporting paper](<https://www.sota2.com/research/paper/6996990909c33900fcd71efc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79fb1e209131cea80723.md>)

Recorded evaluation configuration: {"Mode":"Vision"}. This record does not assert independent reproduction.

### MIRIX

Core Accuracy: 30.94. Result ID: 699af1965698665ec482b61b.

[Reporting paper](<https://www.sota2.com/research/paper/6996990909c33900fcd71efc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79fb1e209131cea80723.md>)

Recorded evaluation configuration: {"Mode":"Text"}. This record does not assert independent reproduction.

### MMA

Core Accuracy: 13.55. Result ID: 699af1965698665ec482b61e.

[Reporting paper](<https://www.sota2.com/research/paper/6996990909c33900fcd71efc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6996990909c33900fcd71efc.md>)

[Implementation](<https://github.com/AIGeeksGroup/MMA>)

Recorded evaluation configuration: {"Mode":"Vision"}. This record does not assert independent reproduction.

### MMA

Core Accuracy: 13.15. Result ID: 699af1965698665ec482b61d.

[Reporting paper](<https://www.sota2.com/research/paper/6996990909c33900fcd71efc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6996990909c33900fcd71efc.md>)

[Implementation](<https://github.com/AIGeeksGroup/MMA>)

Recorded evaluation configuration: {"Mode":"Text"}. This record does not assert independent reproduction.

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