# Object Presence Hallucination Evaluation on POPE MS-COCO 2014 (Random)

Source: [Object Presence Hallucination Evaluation on POPE MS-COCO 2014 (Random)](<https://www.sota2.com/research/sota/object-presence-hallucination-evaluation-on-pope-ms-coco-2014-random>)

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

Data updated: 2026-02-26T05:30:34.892Z

Evaluation of model object presence hallucination using the POPE methodology on the Random subset of the MS-COCO 2014 dataset, reporting Accuracy, Precision, Recall, and F1 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 | Object presence hallucination evaluation |
| Dataset (including any stated split) | POPE MS-COCO 2014 (Random) |
| 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/object-presence-hallucination-evaluation-on-pope-ms-coco-2014-random.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/object-presence-hallucination-evaluation-on-pope-ms-coco-2014-random.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/object-presence-hallucination-evaluation-on-pope-ms-coco-2014-random.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/object-presence-hallucination-evaluation-on-pope-ms-coco-2014-random.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| AVISC | 88.73 | Not recorded | 68fa79051e209131cea7bbb3 |
| AVISC | 87.93 | Not recorded | 68fa79051e209131cea7bbb3 |
| M3ID | 86 | Not recorded | 68fa79051e209131cea7bbb3 |
| VCD | 84.8 | Not recorded | 68fa79051e209131cea7bbb3 |
| base | 84.47 | Not recorded | 68fa79051e209131cea7bbb3 |
| M3ID | 84.37 | Not recorded | 68fa79051e209131cea7bbb3 |
| VCD | 83.37 | Not recorded | 68fa79051e209131cea7bbb3 |
| base | 82.27 | Not recorded | 68fa79051e209131cea7bbb3 |

### AVISC

Accuracy: 88.73. Result ID: 6995b8523badfaffe6b94aaf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79051e209131cea7bbb3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79051e209131cea7bbb3.md>)

[Implementation](<https://sangminwoo.github.io/AvisC/>)

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

### AVISC

Accuracy: 87.93. Result ID: 6995b8523badfaffe6b94ab3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79051e209131cea7bbb3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79051e209131cea7bbb3.md>)

[Implementation](<https://sangminwoo.github.io/AvisC/>)

Recorded evaluation configuration: {"Model":"LLaVA-1.5"}. This record does not assert independent reproduction.

### M3ID

Accuracy: 86. Result ID: 6995b8523badfaffe6b94ab2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79051e209131cea7bbb3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729b1e209131cea5779f.md>)

Recorded evaluation configuration: {"Model":"LLaVA-1.5"}. This record does not assert independent reproduction.

### VCD

Accuracy: 84.8. Result ID: 6995b8523badfaffe6b94ab1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79051e209131cea7bbb3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea5053d.md>)

Recorded evaluation configuration: {"Model":"LLaVA-1.5"}. This record does not assert independent reproduction.

### base

Accuracy: 84.47. Result ID: 6995b8523badfaffe6b94ab0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79051e209131cea7bbb3.md>)

Recorded evaluation configuration: {"Model":"LLaVA-1.5"}. This record does not assert independent reproduction.

### M3ID

Accuracy: 84.37. Result ID: 6995b8523badfaffe6b94aae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79051e209131cea7bbb3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729b1e209131cea5779f.md>)

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

### VCD

Accuracy: 83.37. Result ID: 6995b8523badfaffe6b94aad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79051e209131cea7bbb3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea5053d.md>)

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

### base

Accuracy: 82.27. Result ID: 6995b8523badfaffe6b94aac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79051e209131cea7bbb3.md>)

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

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