# Reasoning-based image editing on RISE-Bench 52 (test)

Source: [Reasoning-based image editing on RISE-Bench 52 (test)](<https://www.sota2.com/research/sota/reasoning-based-image-editing-on-rise-bench-52-test>)

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

Data updated: 2026-06-12T08:31:10.305Z

Evaluation of models on the test split of the RISE-Bench 52 dataset, focusing on reasoning capabilities across Temporal, Causal, Spatial, and Logical dimensions.

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-based image editing |
| Dataset (including any stated split) | RISE-Bench 52 (test) |
| Metric | Temporal Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Temporal Score](<https://www.sota2.com/research/sota/reasoning-based-image-editing-on-rise-bench-52-test.md?metric=Temporal%20Score>): Higher is better; unit: SCALAR.

- [Causal Score](<https://www.sota2.com/research/sota/reasoning-based-image-editing-on-rise-bench-52-test.md?metric=Causal%20Score>): Higher is better; unit: SCALAR.

- [Spatial Score](<https://www.sota2.com/research/sota/reasoning-based-image-editing-on-rise-bench-52-test.md?metric=Spatial%20Score>): Higher is better; unit: SCALAR.

- [Logical Score](<https://www.sota2.com/research/sota/reasoning-based-image-editing-on-rise-bench-52-test.md?metric=Logical%20Score>): Higher is better; unit: SCALAR.

- [Overall Score](<https://www.sota2.com/research/sota/reasoning-based-image-editing-on-rise-bench-52-test.md?metric=Overall%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Temporal Score | Result date | Report paper |
| --- | --- | --- | --- |
| Nano Banana Pro | 41.2 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| InterleaveThinker | 36.5 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| GPT-Image-1 | 34.1 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| InterleaveThinker | 27.1 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| Nano Banana | 25.9 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| Qwen-Image-Edit-2511 | 21.2 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| Seedream-4.0 | 12.9 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| FLUX.2-klein-9B | 7.1 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| BAGEL | 5.9 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| Qwen-Image-Edit | 4.7 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| BAGEL | 2.4 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| FLUX.1-Kontext-Dev | 2.3 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| Ovis-U1 | 1.2 | Not recorded | 6a2b92d9d33dfb23e783b32e |
| Step1X-Edit | 0 | Not recorded | 6a2b92d9d33dfb23e783b32e |

### Nano Banana Pro

Temporal Score: 41.2. Result ID: 6a2bc3b7fbc373592c2a40dc.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

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

### InterleaveThinker

Temporal Score: 36.5. Result ID: 6a2bc3b7fbc373592c2a40e4.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

[Implementation](<https://github.com/zhengdian1/InterleaveThinker>)

Recorded evaluation configuration: {"Base Model":"FLUX.2-klein-9B"}. This record does not assert independent reproduction.

### GPT-Image-1

Temporal Score: 34.1. Result ID: 6a2bc3b7fbc373592c2a40da.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

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

### InterleaveThinker

Temporal Score: 27.1. Result ID: 6a2bc3b7fbc373592c2a40e6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

[Implementation](<https://github.com/zhengdian1/InterleaveThinker>)

Recorded evaluation configuration: {"Base Model":"Qwen-Image-Edit-2511"}. This record does not assert independent reproduction.

### Nano Banana

Temporal Score: 25.9. Result ID: 6a2bc3b7fbc373592c2a40db.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

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

### Qwen-Image-Edit-2511

Temporal Score: 21.2. Result ID: 6a2bc3b7fbc373592c2a40e5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

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

Recorded evaluation configuration: {"Category":"Open-source Models"}. This record does not assert independent reproduction.

### Seedream-4.0

Temporal Score: 12.9. Result ID: 6a2bc3b7fbc373592c2a40d9.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

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

### FLUX.2-klein-9B

Temporal Score: 7.1. Result ID: 6a2bc3b7fbc373592c2a40e3.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

Recorded evaluation configuration: {"Category":"Open-source Models"}. This record does not assert independent reproduction.

### BAGEL

Temporal Score: 5.9. Result ID: 6a2bc3b7fbc373592c2a40e1.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a311e209131cea81aad.md>)

[Implementation](<https://bagel-ai.org/>)

Recorded evaluation configuration: {"Category":"Open-source Models","CoT":"true"}. This record does not assert independent reproduction.

### Qwen-Image-Edit

Temporal Score: 4.7. Result ID: 6a2bc3b7fbc373592c2a40e2.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

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

Recorded evaluation configuration: {"Category":"Open-source Models"}. This record does not assert independent reproduction.

### BAGEL

Temporal Score: 2.4. Result ID: 6a2bc3b7fbc373592c2a40e0.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a311e209131cea81aad.md>)

[Implementation](<https://bagel-ai.org/>)

Recorded evaluation configuration: {"Category":"Open-source Models","CoT":"false"}. This record does not assert independent reproduction.

### FLUX.1-Kontext-Dev

Temporal Score: 2.3. Result ID: 6a2bc3b7fbc373592c2a40df.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79a81e209131cea7eb79.md>)

Recorded evaluation configuration: {"Category":"Open-source Models"}. This record does not assert independent reproduction.

### Ovis-U1

Temporal Score: 1.2. Result ID: 6a2bc3b7fbc373592c2a40de.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79cd1e209131cea7f6ec.md>)

Recorded evaluation configuration: {"Category":"Open-source Models"}. This record does not assert independent reproduction.

### Step1X-Edit

Temporal Score: 0. Result ID: 6a2bc3b7fbc373592c2a40dd.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d9d33dfb23e783b32e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a551e209131cea82892.md>)

[Implementation](<https://github.com/stepfun-ai/Step1X-Edit>)

Recorded evaluation configuration: {"Category":"Open-source Models"}. This record does not assert independent reproduction.

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