Image modelNo status listed

Stable Diffusion 3.5 Large

Stability AI

Released: October 22, 2024
Data date: August 15, 2026

Category view

Position within the category

This overview uses only published data from matching cohorts. Missing values never change a rank.

This position gives equal weight to 4 fixed Gradually image tests. One archived first output contributes for each model and task.

Position: Rank 28 of 28
Index score: 2.5 / 100
Coverage: 4 / 4

Leaderboard

1MAI-Image-2.5 Flash76.6 / 100

2GPT Image 271 / 100

3MAI-Image-2.567.6 / 100

27HiDream-O1-Image14.2 / 100

28Stable Diffusion 3.5 Large2.5 / 100

Source: Gradually-Bildtest

Measurements

Comparable benchmark results

Each chart contains exactly one source, one measurement series, and one stored comparison cohort. Bars show the position. The measured value appears on the right.

WISE Verified overall

40.4% · Rank 4 of 4

Sample: 1,000 · Data date: August 26, 2026

1.Nano Banana Pro87.6%

2.GPT Image 1.582.5%

3.FLUX.2 Klein 9B44%

4.Stable Diffusion 3.5 Large40.4%

4 of 4 model versions shown in this chart. A higher value ranks first.

1,000 knowledge and realism tasks. Binary item judgments are averaged by category, and the overall score follows the published weighting.

Source: WISE VerifiedParticipants: 4

WISE culture

49% · Rank 3 of 4

Data date: August 26, 2026

1.Nano Banana Pro89.75%

2.GPT Image 1.589%

3.FLUX.2 Klein 9B49%

3.Stable Diffusion 3.5 Large49%

4 of 4 model versions shown in this chart. A higher value ranks first.

1,000 knowledge and realism tasks. Binary item judgments are averaged by category, and the overall score follows the published weighting.

Source: WISE VerifiedParticipants: 4

WISE time

40.83% · Rank 3 of 4

Data date: August 26, 2026

1.Nano Banana Pro81.67%

2.GPT Image 1.569.17%

3.Stable Diffusion 3.5 Large40.83%

4.FLUX.2 Klein 9B39.17%

4 of 4 model versions shown in this chart. A higher value ranks first.

1,000 knowledge and realism tasks. Binary item judgments are averaged by category, and the overall score follows the published weighting.

Source: WISE VerifiedParticipants: 4

WISE space

44.17% · Rank 4 of 4

Data date: August 26, 2026

1.Nano Banana Pro93.33%

2.GPT Image 1.588.33%

3.FLUX.2 Klein 9B55%

4.Stable Diffusion 3.5 Large44.17%

4 of 4 model versions shown in this chart. A higher value ranks first.

1,000 knowledge and realism tasks. Binary item judgments are averaged by category, and the overall score follows the published weighting.

Source: WISE VerifiedParticipants: 4

WISE biology

30% · Rank 4 of 4

Data date: August 26, 2026

1.Nano Banana Pro81.67%

2.GPT Image 1.580%

3.FLUX.2 Klein 9B38.33%

4.Stable Diffusion 3.5 Large30%

4 of 4 model versions shown in this chart. A higher value ranks first.

1,000 knowledge and realism tasks. Binary item judgments are averaged by category, and the overall score follows the published weighting.

Source: WISE VerifiedParticipants: 4

WISE physics

37.5% · Rank 4 of 4

Data date: August 26, 2026

1.Nano Banana Pro86.67%

2.GPT Image 1.575.83%

3.FLUX.2 Klein 9B48.33%

4.Stable Diffusion 3.5 Large37.5%

4 of 4 model versions shown in this chart. A higher value ranks first.

1,000 knowledge and realism tasks. Binary item judgments are averaged by category, and the overall score follows the published weighting.

Source: WISE VerifiedParticipants: 4

WISE chemistry

20.83% · Rank 4 of 4

Data date: August 26, 2026

1.Nano Banana Pro87.5%

2.GPT Image 1.577.5%

3.FLUX.2 Klein 9B22.5%

4.Stable Diffusion 3.5 Large20.83%

4 of 4 model versions shown in this chart. A higher value ranks first.

1,000 knowledge and realism tasks. Binary item judgments are averaged by category, and the overall score follows the published weighting.

Source: WISE VerifiedParticipants: 4

Gradually sample test: Typography and layout

0 rank points · Rank 28 of 28

Sample: 1 · Data date: August 18, 2026

1.MAI-Image-2.593.8 rank points

26.HiDream-O1-Image6.2 rank points

26.Midjourney V8.16.2 rank points

28.Stable Diffusion 3.5 Large0 rank points

4 of 28 model versions shown in this chart. A higher value ranks first.

One archived, unfiltered first output per model. All 28 images are ranked in three model-blind orderings. The 0-100 value normalizes the mean rank. This remains an n = 1 sample, and an automated judge may have visual preferences of its own.

Source: Gradually-BildtestParticipants: 28