# Multi-reference image generation on OmniRef-Bench 1.0 (test)

Source: [Multi-reference image generation on OmniRef-Bench 1.0 (test)](<https://www.sota2.com/research/sota/multi-reference-image-generation-on-omniref-bench-1-0-test>)

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

Data updated: 2026-06-26T08:47:57.327Z

Evaluation of Multi-reference Image Generation models on the test split of OmniRef-Bench version 1.0, assessed using correlation metrics (PLCC, SROCC, KROCC) and a general 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 | Multi-reference image generation |
| Dataset (including any stated split) | OmniRef-Bench 1.0 (test) |
| Metric | Score |
| Unit | SCALAR |
| 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

- [Score](<https://www.sota2.com/research/sota/multi-reference-image-generation-on-omniref-bench-1-0-test.md?metric=Score>): Higher is better; unit: SCALAR.

- [PLCC](<https://www.sota2.com/research/sota/multi-reference-image-generation-on-omniref-bench-1-0-test.md?metric=PLCC>): Higher is better; unit: SCALAR.

- [SROCC](<https://www.sota2.com/research/sota/multi-reference-image-generation-on-omniref-bench-1-0-test.md?metric=SROCC>): Higher is better; unit: SCALAR.

- [KROCC](<https://www.sota2.com/research/sota/multi-reference-image-generation-on-omniref-bench-1-0-test.md?metric=KROCC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| Nano Banana Pro | 8.5 | Not recorded | 6a3e0791206542251d7cb496 |
| DyRef | 8.38 | Not recorded | 6a3e0791206542251d7cb496 |
| Seedream4.5 | 8.13 | Not recorded | 6a3e0791206542251d7cb496 |
| Qwen-2511 | 4.97 | Not recorded | 6a3e0791206542251d7cb496 |
| DyRef | 3.42 | Not recorded | 6a3e0791206542251d7cb496 |
| Nano Banana Pro | 3.09 | Not recorded | 6a3e0791206542251d7cb496 |
| Seedream4.5 | 2.26 | Not recorded | 6a3e0791206542251d7cb496 |
| Qwen-2511 | 1.22 | Not recorded | 6a3e0791206542251d7cb496 |

### Nano Banana Pro

Score: 8.5. Result ID: 6a3e3cbafbc373592c607c09.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

Recorded evaluation configuration: {"Evaluation Setup":"Gemini3 Flash","Score Range":"1-10"}. This record does not assert independent reproduction.

### DyRef

Score: 8.38. Result ID: 6a3e3cbafbc373592c607c07.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

Recorded evaluation configuration: {"Evaluation Setup":"Gemini3 Flash","Score Range":"1-10"}. This record does not assert independent reproduction.

### Seedream4.5

Score: 8.13. Result ID: 6a3e3cbafbc373592c607c0b.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba51e209131cea89983.md>)

Recorded evaluation configuration: {"Evaluation Setup":"Gemini3 Flash","Score Range":"1-10"}. This record does not assert independent reproduction.

### Qwen-2511

Score: 4.97. Result ID: 6a3e3cbafbc373592c607c0d.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a6a1e209131cea83137.md>)

Recorded evaluation configuration: {"Evaluation Setup":"Gemini3 Flash","Score Range":"1-10"}. This record does not assert independent reproduction.

### DyRef

Score: 3.42. Result ID: 6a3e3cbafbc373592c607c08.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

Recorded evaluation configuration: {"Evaluation Setup":"Human","Score Range":"1-4"}. This record does not assert independent reproduction.

### Nano Banana Pro

Score: 3.09. Result ID: 6a3e3cbafbc373592c607c0a.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

Recorded evaluation configuration: {"Evaluation Setup":"Human","Score Range":"1-4"}. This record does not assert independent reproduction.

### Seedream4.5

Score: 2.26. Result ID: 6a3e3cbafbc373592c607c0c.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba51e209131cea89983.md>)

Recorded evaluation configuration: {"Evaluation Setup":"Human","Score Range":"1-4"}. This record does not assert independent reproduction.

### Qwen-2511

Score: 1.22. Result ID: 6a3e3cbafbc373592c607c0e.

[Reporting paper](<https://www.sota2.com/research/paper/6a3e0791206542251d7cb496.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a6a1e209131cea83137.md>)

Recorded evaluation configuration: {"Evaluation Setup":"Human","Score Range":"1-4"}. This record does not assert independent reproduction.

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