# Multimodal Generation on Amazon-Beauty (test)

Source: [Multimodal Generation on Amazon-Beauty (test)](<https://www.sota2.com/research/sota/multimodal-generation-on-amazon-beauty-test>)

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

Data updated: 2026-02-26T05:38:34.716Z

Evaluation of multimodal generation capabilities using the test split of the Amazon Beauty dataset, measured by CLIP similarity scores (I2, IT), Perplexity, and KL Divergence.

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 | Multimodal Generation |
| Dataset (including any stated split) | Amazon-Beauty (test) |
| Metric | CLIP-I2 |
| 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

- [CLIP-I2](<https://www.sota2.com/research/sota/multimodal-generation-on-amazon-beauty-test.md?metric=CLIP-I2>): Higher is better; unit: PERCENT.

- [Perplexity](<https://www.sota2.com/research/sota/multimodal-generation-on-amazon-beauty-test.md?metric=Perplexity>): Lower is better; unit: SCALAR.

- [CLIP-IT](<https://www.sota2.com/research/sota/multimodal-generation-on-amazon-beauty-test.md?metric=CLIP-IT>): Higher is better; unit: PERCENT.

- [KL Divergence](<https://www.sota2.com/research/sota/multimodal-generation-on-amazon-beauty-test.md?metric=KL%20Divergence>): Lower is better; unit: SCALAR.

## Recorded results

| Method | CLIP-I2 | Result date | Report paper |
| --- | --- | --- | --- |
| GRAPHGPT-O | 63.46 | Not recorded | 68fa775d1e209131cea72c0c |
| DreamLLM | 60.5 | Not recorded | 68fa775d1e209131cea72c0c |
| GRAPHGPT-O | 57.99 | Not recorded | 68fa775d1e209131cea72c0c |
| Emu3 | 45.82 | Not recorded | 68fa775d1e209131cea72c0c |
| Chameleon | 43.73 | Not recorded | 68fa775d1e209131cea72c0c |
| Janus | 42.52 | Not recorded | 68fa775d1e209131cea72c0c |

### GRAPHGPT-O

CLIP-I2: 63.46. Result ID: 699499833a6c3148491e5055.

[Reporting paper](<https://www.sota2.com/research/paper/68fa775d1e209131cea72c0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa775d1e209131cea72c0c.md>)

Recorded evaluation configuration: {"Type":"Soft"}. This record does not assert independent reproduction.

### DreamLLM

CLIP-I2: 60.5. Result ID: 699499833a6c3148491e5053.

[Reporting paper](<https://www.sota2.com/research/paper/68fa775d1e209131cea72c0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72941e209131cea5742f.md>)

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

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

### GRAPHGPT-O

CLIP-I2: 57.99. Result ID: 699499833a6c3148491e5054.

[Reporting paper](<https://www.sota2.com/research/paper/68fa775d1e209131cea72c0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa775d1e209131cea72c0c.md>)

Recorded evaluation configuration: {"Type":"Hard"}. This record does not assert independent reproduction.

### Emu3

CLIP-I2: 45.82. Result ID: 699499833a6c3148491e5051.

[Reporting paper](<https://www.sota2.com/research/paper/68fa775d1e209131cea72c0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa732a1e209131cea5add9.md>)

[Implementation](<https://github.com/baaivision/Emu>)

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

### Chameleon

CLIP-I2: 43.73. Result ID: 699499833a6c3148491e5052.

[Reporting paper](<https://www.sota2.com/research/paper/68fa775d1e209131cea72c0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77971e209131cea74348.md>)

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

### Janus

CLIP-I2: 42.52. Result ID: 699499833a6c3148491e5050.

[Reporting paper](<https://www.sota2.com/research/paper/68fa775d1e209131cea72c0c.md>)

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

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