# AIGC Detection on SynthWildX (MJ)

Source: [AIGC Detection on SynthWildX (MJ)](<https://www.sota2.com/research/sota/aigc-detection-on-synthwildx-mj>)

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

Data updated: 2026-03-17T07:00:51.126Z

Evaluation of AIGC Detection performance on the SynthWildX dataset, specifically focusing on the Midjourney (MJ) subset, reporting metrics like AP and AUC.

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 | AIGC Detection |
| Dataset (including any stated split) | SynthWildX (MJ) |
| Metric | AP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [AP](<https://www.sota2.com/research/sota/aigc-detection-on-synthwildx-mj.md?metric=AP>): Higher is better; unit: PERCENT.

- [AUC](<https://www.sota2.com/research/sota/aigc-detection-on-synthwildx-mj.md?metric=AUC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP | Result date | Report paper |
| --- | --- | --- | --- |
| CNNSpot | 87.19 | Not recorded | 68fa77af1e209131cea74b68 |
| FakeScope | 83.72 | Not recorded | 68fa77af1e209131cea74b68 |
| FakeScope | 81.99 | Not recorded | 68fa77af1e209131cea74b68 |
| LLaVA-v1.5 | 54.7 | Not recorded | 68fa77af1e209131cea74b68 |
| FreDect | 50.99 | Not recorded | 68fa77af1e209131cea74b68 |
| InstructBLIP | 49.56 | Not recorded | 68fa77af1e209131cea74b68 |
| InternLM-XC.2-vl | 48.39 | Not recorded | 68fa77af1e209131cea74b68 |
| mPLUG-Owl2 | 47.67 | Not recorded | 68fa77af1e209131cea74b68 |
| UnivFD | 45.88 | Not recorded | 68fa77af1e209131cea74b68 |
| CLIP-ViT-Large-14 | 42.37 | Not recorded | 68fa77af1e209131cea74b68 |
| IDEFICS-Instruct | 40.29 | Not recorded | 68fa77af1e209131cea74b68 |
| Qwen-VL | 34.85 | Not recorded | 68fa77af1e209131cea74b68 |

### CNNSpot

AP: 87.19. Result ID: 69b8fc1b47f34ce924a0ed39.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67581e209131cea15b26.md>)

Recorded evaluation configuration: {"Protocol":"training-based"}. This record does not assert independent reproduction.

### FakeScope

AP: 83.72. Result ID: 69b8fc1b47f34ce924a0ed43.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

Recorded evaluation configuration: {"Backbone":"mPLUG-Owl2"}. This record does not assert independent reproduction.

### FakeScope

AP: 81.99. Result ID: 69b8fc1b47f34ce924a0ed44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-v1.5"}. This record does not assert independent reproduction.

### LLaVA-v1.5

AP: 54.7. Result ID: 69b8fc1b47f34ce924a0ed41.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Backbone":"Vicuna-7B","Protocol":"baseline"}. This record does not assert independent reproduction.

### FreDect

AP: 50.99. Result ID: 69b8fc1b47f34ce924a0ed3b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d11e209131cea18aaa.md>)

Recorded evaluation configuration: {"Protocol":"training-based"}. This record does not assert independent reproduction.

### InstructBLIP

AP: 49.56. Result ID: 69b8fc1b47f34ce924a0ed3e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea47021.md>)

[Implementation](<https://github.com/salesforce/LAVIS/tree/main/projects/instructblip>)

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

### InternLM-XC.2-vl

AP: 48.39. Result ID: 69b8fc1b47f34ce924a0ed3d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72021e209131cea541e3.md>)

[Implementation](<https://github.com/InternLM/InternLM-XComposer>)

Recorded evaluation configuration: {"Backbone":"InternLM2-7B"}. This record does not assert independent reproduction.

### mPLUG-Owl2

AP: 47.67. Result ID: 69b8fc1b47f34ce924a0ed42.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f575.md>)

[Implementation](<https://github.com/X-PLUG/mPLUG-Owl/tree/main/mPLUG-Owl2>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Protocol":"baseline"}. This record does not assert independent reproduction.

### UnivFD

AP: 45.88. Result ID: 69b8fc1b47f34ce924a0ed3a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b11e209131cea57ee9.md>)

Recorded evaluation configuration: {"Protocol":"training-based"}. This record does not assert independent reproduction.

### CLIP-ViT-Large-14

AP: 42.37. Result ID: 69b8fc1b47f34ce924a0ed3c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

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

### IDEFICS-Instruct

AP: 40.29. Result ID: 69b8fc1b47f34ce924a0ed40.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70581e209131cea4a712.md>)

[Implementation](<https://github.com/huggingface/OBELICS>)

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

### Qwen-VL

AP: 34.85. Result ID: 69b8fc1b47f34ce924a0ed3f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77af1e209131cea74b68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d41e209131cea4d774.md>)

[Implementation](<https://github.com/QwenLM/Qwen-VL>)

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

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