# Hallucination Benchmark on POPE-P

Source: [Hallucination Benchmark on POPE-P](<https://www.sota2.com/research/sota/hallucination-benchmark-on-pope-p>)

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

Data updated: 2026-04-14T08:50:59.528Z

Evaluation of model hallucination capabilities using the POPE-P dataset/split, reporting standard classification metrics such as 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 | Hallucination Benchmark |
| Dataset (including any stated split) | POPE-P |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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/hallucination-benchmark-on-pope-p.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| V-STAR | 87.3 | Not recorded | 69ddca347d0172140ec79b45 |
| ThinkLite-VL | 86.7 | Not recorded | 69ddca347d0172140ec79b45 |
| Vision-R1 | 85.2 | Not recorded | 69ddca347d0172140ec79b45 |
| VL-Cogito | 85 | Not recorded | 69ddca347d0172140ec79b45 |
| R1-Onevision | 84 | Not recorded | 69ddca347d0172140ec79b45 |
| Qwen2.5VL | 83.2 | Not recorded | 69ddca347d0172140ec79b45 |
| OpenVLThinker | 82.5 | Not recorded | 69ddca347d0172140ec79b45 |
| VL-Rethinker | 81.8 | Not recorded | 69ddca347d0172140ec79b45 |

### V-STAR

Accuracy: 87.3. Result ID: 69ddff8147f34ce924c5810c.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b45.md>)

Recorded evaluation configuration: {"Data Size":"40k"}. This record does not assert independent reproduction.

### ThinkLite-VL

Accuracy: 86.7. Result ID: 69ddff8147f34ce924c5810b.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa790c1e209131cea7bdde.md>)

Recorded evaluation configuration: {"Data Size":"11k"}. This record does not assert independent reproduction.

### Vision-R1

Accuracy: 85.2. Result ID: 69ddff8147f34ce924c58107.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77591e209131cea72979.md>)

Recorded evaluation configuration: {"Data Size":"210k"}. This record does not assert independent reproduction.

### VL-Cogito

Accuracy: 85. Result ID: 69ddff8147f34ce924c58109.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a531e209131cea82780.md>)

Recorded evaluation configuration: {"Data Size":"80k"}. This record does not assert independent reproduction.

### R1-Onevision

Accuracy: 84. Result ID: 69ddff8147f34ce924c58106.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77771e209131cea7357a.md>)

Recorded evaluation configuration: {"Data Size":"155k"}. This record does not assert independent reproduction.

### Qwen2.5VL

Accuracy: 83.2. Result ID: 69ddff8147f34ce924c58105.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b45.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### OpenVLThinker

Accuracy: 82.5. Result ID: 69ddff8147f34ce924c5810a.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a251e209131cea814a7.md>)

Recorded evaluation configuration: {"Data Size":"59.2k"}. This record does not assert independent reproduction.

### VL-Rethinker

Accuracy: 81.8. Result ID: 69ddff8147f34ce924c58108.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca347d0172140ec79b45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78791e209131cea788a8.md>)

Recorded evaluation configuration: {"Data Size":"39k"}. This record does not assert independent reproduction.

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