# Text-to-Image Human Preference on Arena T2I Leaderboard

Source: [Text-to-Image Human Preference on Arena T2I Leaderboard](<https://www.sota2.com/research/sota/text-to-image-human-preference-on-arena-t2i-leaderboard>)

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

Data updated: 2026-07-01T08:24:36.877Z

Evaluation of Text-to-Image model performance based on human preference judgments collected via the Arena T2I Leaderboard, measured by Arena rank and 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 | Text-to-Image Human Preference |
| Dataset (including any stated split) | Arena T2I Leaderboard |
| Metric | Arena Rank |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 11 of 11 |
| 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

- [Arena Rank](<https://www.sota2.com/research/sota/text-to-image-human-preference-on-arena-t2i-leaderboard.md?metric=Arena%20Rank>): Lower is better; unit: SCALAR.

- [Arena Score](<https://www.sota2.com/research/sota/text-to-image-human-preference-on-arena-t2i-leaderboard.md?metric=Arena%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Arena Rank | Result date | Report paper |
| --- | --- | --- | --- |
| gemini-3-pro-image-preview-2k | 3 | Not recorded | 6a449f15e0224bd4f49931c2 |
| gpt-image-1.5-high-fidelity | 4 | Not recorded | 6a449f15e0224bd4f49931c2 |
| grok-imagine-image-20260306 | 8 | Not recorded | 6a449f15e0224bd4f49931c2 |
| gemini-2.5-flash-image (nano-banana) | 14 | Not recorded | 6a449f15e0224bd4f49931c2 |
| hunyuan-image-3.0-fal | 15 | Not recorded | 6a449f15e0224bd4f49931c2 |
| imagen-4.0-ultra-generate-001 | 17 | Not recorded | 6a449f15e0224bd4f49931c2 |
| wan2.6-t2i-v2 | 21 | Not recorded | 6a449f15e0224bd4f49931c2 |
| imagen-4.0-generate-001 | 22 | Not recorded | 6a449f15e0224bd4f49931c2 |
| gpt-image-1 | 27 | Not recorded | 6a449f15e0224bd4f49931c2 |
| recraft-v4 | 29 | Not recorded | 6a449f15e0224bd4f49931c2 |
| ideogram-v3-quality | 42 | Not recorded | 6a449f15e0224bd4f49931c2 |

### gemini-3-pro-image-preview-2k

Arena Rank: 3. Result ID: 6a44cec473d097d845bf5bee.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f49931c2.md>)

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

### gpt-image-1.5-high-fidelity

Arena Rank: 4. Result ID: 6a44cec473d097d845bf5bf0.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f49931c2.md>)

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

### grok-imagine-image-20260306

Arena Rank: 8. Result ID: 6a44cec473d097d845bf5bef.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f49931c2.md>)

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

### gemini-2.5-flash-image (nano-banana)

Arena Rank: 14. Result ID: 6a44cec473d097d845bf5bf3.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f49931c2.md>)

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

### hunyuan-image-3.0-fal

Arena Rank: 15. Result ID: 6a44cec473d097d845bf5bf7.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f49931c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb51e209131cea8a0c1.md>)

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

### imagen-4.0-ultra-generate-001

Arena Rank: 17. Result ID: 6a44cec473d097d845bf5bf5.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f49931c2.md>)

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

### wan2.6-t2i-v2

Arena Rank: 21. Result ID: 6a44cec473d097d845bf5bf2.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f49931c2.md>)

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

### imagen-4.0-generate-001

Arena Rank: 22. Result ID: 6a44cec473d097d845bf5bf6.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f49931c2.md>)

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

### gpt-image-1

Arena Rank: 27. Result ID: 6a44cec473d097d845bf5bf4.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f49931c2.md>)

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

### recraft-v4

Arena Rank: 29. Result ID: 6a44cec473d097d845bf5bf1.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f49931c2.md>)

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

### ideogram-v3-quality

Arena Rank: 42. Result ID: 6a44cec473d097d845bf5bf8.

[Reporting paper](<https://www.sota2.com/research/paper/6a449f15e0224bd4f49931c2.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.