# Relational Match-to-Sample on RMTS 256 shape-color combinations (test)

Source: [Relational Match-to-Sample on RMTS 256 shape-color combinations (test)](<https://www.sota2.com/research/sota/relational-match-to-sample-on-rmts-256-shape-color-combinations-test>)

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

Data updated: 2026-02-26T05:30:09.688Z

Evaluation of Relational Match-to-Sample (RMTS) performance on the test split of the RMTS 256 shape-color combinations dataset, measured using 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 | Relational Match-to-Sample (RMTS) |
| Dataset (including any stated split) | RMTS 256 shape-color combinations 1.0 (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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/relational-match-to-sample-on-rmts-256-shape-color-combinations-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CLIP | 98.3 | Not recorded | 68fa75d11e209131cea6a00d |
| DINOv2 | 98.2 | Not recorded | 68fa75d11e209131cea6a00d |
| MAE | 93.4 | Not recorded | 68fa75d11e209131cea6a00d |
| ImageNet | 89.3 | Not recorded | 68fa75d11e209131cea6a00d |
| DINO | 87.7 | Not recorded | 68fa75d11e209131cea6a00d |
| Baseline (Random) | 50.1 | Not recorded | 68fa75d11e209131cea6a00d |

### CLIP

Accuracy: 98.3. Result ID: 6993fda23a6c3148491a2176.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a00d.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pretraining Scale":"400M"}. This record does not assert independent reproduction.

### DINOv2

Accuracy: 98.2. Result ID: 6993fda23a6c3148491a2177.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a00d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72181e209131cea546c3.md>)

[Implementation](<https://github.com/facebookresearch/dinov2>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pretraining Scale":"142M"}. This record does not assert independent reproduction.

### MAE

Accuracy: 93.4. Result ID: 6993fda23a6c3148491a217a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a00d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7f1e209131cea2e973.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pretraining Scale":"1.28M"}. This record does not assert independent reproduction.

### ImageNet

Accuracy: 89.3. Result ID: 6993fda23a6c3148491a2178.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a00d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pretraining Scale":"14.2M"}. This record does not assert independent reproduction.

### DINO

Accuracy: 87.7. Result ID: 6993fda23a6c3148491a2179.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a00d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea2594c.md>)

[Implementation](<https://github.com/facebookresearch/dino>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pretraining Scale":"1.28M"}. This record does not assert independent reproduction.

### Baseline (Random)

Accuracy: 50.1. Result ID: 6993fda23a6c3148491a217b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a00d.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

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