# Reasoning Segmentation on HALLUSEGBENCH Reasoning

Source: [Reasoning Segmentation on HALLUSEGBENCH Reasoning](<https://www.sota2.com/research/sota/reasoning-segmentation-on-hallusegbench-reasoning>)

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

Data updated: 2026-04-24T07:43:46.700Z

Evaluation of Reasoning Segmentation performance on the HALLUSEGBENCH Reasoning dataset, reporting CMS Factual, CMS Counterfactual, ∆IoU Textual, and ∆IoU Visual metrics.

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 | Reasoning Segmentation |
| Dataset (including any stated split) | HALLUSEGBENCH Reasoning |
| Metric | CMS Factual |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [CMS Factual](<https://www.sota2.com/research/sota/reasoning-segmentation-on-hallusegbench-reasoning.md?metric=CMS%20Factual>): Higher is better; unit: SCALAR.

- [CMS Counterfactual](<https://www.sota2.com/research/sota/reasoning-segmentation-on-hallusegbench-reasoning.md?metric=CMS%20Counterfactual>): Higher is better; unit: SCALAR.

- [∆IoU Textual](<https://www.sota2.com/research/sota/reasoning-segmentation-on-hallusegbench-reasoning.md?metric=%E2%88%86IoU%20Textual>): Higher is better; unit: SCALAR.

- [∆IoU Visual](<https://www.sota2.com/research/sota/reasoning-segmentation-on-hallusegbench-reasoning.md?metric=%E2%88%86IoU%20Visual>): Higher is better; unit: SCALAR.

## Recorded results

| Method | CMS Factual | Result date | Report paper |
| --- | --- | --- | --- |
| VisionReasoner | 0.7315 | Not recorded | 68fa79ba1e209131cea7f22e |
| Seg-Zero | 0.6554 | Not recorded | 68fa79ba1e209131cea7f22e |
| LISA-13B | 0.4979 | Not recorded | 68fa79ba1e209131cea7f22e |
| LISA-7B | 0.4438 | Not recorded | 68fa79ba1e209131cea7f22e |
| PixelLM-7B | 0.4284 | Not recorded | 68fa79ba1e209131cea7f22e |
| PixelLM-13B | 0.4267 | Not recorded | 68fa79ba1e209131cea7f22e |
| GLaMM-7B | 0.3556 | Not recorded | 68fa79ba1e209131cea7f22e |
| SESAME-7B | 0.2998 | Not recorded | 68fa79ba1e209131cea7f22e |
| RobustSeg | 0.1541 | Not recorded | 68fa79ba1e209131cea7f22e |

### VisionReasoner

CMS Factual: 0.7315. Result ID: 69eb1f2847f34ce924d30d26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ba1e209131cea7f22e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba21e209131cea897a6.md>)

Recorded evaluation configuration: {"Hallucination Mitigation":"true"}. This record does not assert independent reproduction.

### Seg-Zero

CMS Factual: 0.6554. Result ID: 69eb1f2847f34ce924d30d25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ba1e209131cea7f22e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79b81e209131cea7f19c.md>)

Recorded evaluation configuration: {"Hallucination Mitigation":"true"}. This record does not assert independent reproduction.

### LISA-13B

CMS Factual: 0.4979. Result ID: 69eb1f2847f34ce924d30d23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ba1e209131cea7f22e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa730a1e209131cea5a0b2.md>)

[Implementation](<https://www.sota2.com/github.com/dvlab-research/LISA>)

Recorded evaluation configuration: {"Hallucination Mitigation":"false"}. This record does not assert independent reproduction.

### LISA-7B

CMS Factual: 0.4438. Result ID: 69eb1f2847f34ce924d30d20.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ba1e209131cea7f22e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa730a1e209131cea5a0b2.md>)

[Implementation](<https://www.sota2.com/github.com/dvlab-research/LISA>)

Recorded evaluation configuration: {"Hallucination Mitigation":"false"}. This record does not assert independent reproduction.

### PixelLM-7B

CMS Factual: 0.4284. Result ID: 69eb1f2847f34ce924d30d21.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ba1e209131cea7f22e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74241e209131cea5ff3b.md>)

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

Recorded evaluation configuration: {"Hallucination Mitigation":"false"}. This record does not assert independent reproduction.

### PixelLM-13B

CMS Factual: 0.4267. Result ID: 69eb1f2847f34ce924d30d24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ba1e209131cea7f22e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74241e209131cea5ff3b.md>)

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

Recorded evaluation configuration: {"Hallucination Mitigation":"false"}. This record does not assert independent reproduction.

### GLaMM-7B

CMS Factual: 0.3556. Result ID: 69eb1f2847f34ce924d30d22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ba1e209131cea7f22e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73651e209131cea5c2d8.md>)

[Implementation](<https://mbzuai-oryx.github.io/groundingLMM>)

Recorded evaluation configuration: {"Hallucination Mitigation":"false"}. This record does not assert independent reproduction.

### SESAME-7B

CMS Factual: 0.2998. Result ID: 69eb1f2847f34ce924d30d27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ba1e209131cea7f22e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71701e209131cea513b6.md>)

Recorded evaluation configuration: {"Hallucination Mitigation":"true"}. This record does not assert independent reproduction.

### RobustSeg

CMS Factual: 0.1541. Result ID: 69eb1f2847f34ce924d30d28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ba1e209131cea7f22e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ba1e209131cea7f22e.md>)

Recorded evaluation configuration: {"Hallucination Mitigation":"true"}. This record does not assert independent reproduction.

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