# Tactile Object Recognition on GelSight Mini

Source: [Tactile Object Recognition on GelSight Mini](<https://www.sota2.com/research/sota/tactile-object-recognition-on-gelsight-mini>)

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

Data updated: 2026-06-04T12:11:21.404Z

Evaluation of model performance on tactile object recognition using the GelSight Mini dataset, measured by Weighted Semantic 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 | Tactile Object Recognition |
| Dataset (including any stated split) | GelSight Mini |
| Metric | Weighted Semantic Score |
| 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

- [Weighted Semantic Score](<https://www.sota2.com/research/sota/tactile-object-recognition-on-gelsight-mini.md?metric=Weighted%20Semantic%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Weighted Semantic Score | Result date | Report paper |
| --- | --- | --- | --- |
| ChatGPT-VLM | 30.2 | Not recorded | 6a2106f9c10484bac23f06c5 |
| Qwen-VLM | 28.7 | Not recorded | 6a2106f9c10484bac23f06c5 |
| YOLO-E | 16.9 | Not recorded | 6a2106f9c10484bac23f06c5 |
| YOLO-World | 15.3 | Not recorded | 6a2106f9c10484bac23f06c5 |

### ChatGPT-VLM

Weighted Semantic Score: 30.2. Result ID: 6a216b4ffbc373592c1e700c.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06c5.md>)

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

### Qwen-VLM

Weighted Semantic Score: 28.7. Result ID: 6a216b4ffbc373592c1e700b.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06c5.md>)

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

### YOLO-E

Weighted Semantic Score: 16.9. Result ID: 6a216b4ffbc373592c1e700e.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c3c1e209131cea8d10c.md>)

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

### YOLO-World

Weighted Semantic Score: 15.3. Result ID: 6a216b4ffbc373592c1e700d.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106f9c10484bac23f06c5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72411e209131cea554fe.md>)

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

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