LMArena Text to Image: 3D modeling
1,113.36 points
Rank 45 · 2,522 samples · Retrieved August 26, 2026
LMArenaImage modelNo status listed
Krea 2 Large
Krea
- Released
- May 2026
- 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 6 of 28
- Index score
- 63.6 / 100
- Coverage
- 4 / 4
Leaderboard
1MAI-Image-2.5 Flash76.6 / 100
2GPT Image 271 / 100
3MAI-Image-2.567.6 / 100
5HiDream-O1-Image-1.564.5 / 100
6Krea 2 Large, Current model63.6 / 100
7FLUX.2 Max63 / 100
28Stable Diffusion 3.5 Large2.5 / 100
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.
Text to Image Arena
1,221 Elo · Rank 18 of 25
Sample: 13,981 · Data date: August 26, 2026
1.GPT Image 21,371 Elo
16.Ideogram 4.01,223 Elo
17.Luma UNI 1 Max1,222 Elo
18.Krea 2 Large, Current model1,221 Elo
19.Recraft V4.1 Utility1,218 Elo
20.Krea 2 Medium Turbo1,215 Elo
25.FLUX.2 Klein 9B1,144 Elo
7 of 25 model versions shown in this chart. A higher value ranks first.
Source: Artificial AnalysisParticipants: 25
Gradually sample test: Typography and layout
46.9 rank points · Rank 14 of 28
Sample: 1 · Data date: August 18, 2026
1.MAI-Image-2.593.8 rank points
11.Luma UNI 1 Max50.6 rank points
13.HiDream-O1-Image-1.549.4 rank points
14.Krea 2 Large, Current model46.9 rank points
15.Ideogram 4.045.7 rank points
15.MAI-Image-2.5 Flash45.7 rank points
28.Stable Diffusion 3.5 Large0 rank points
7 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
Gradually sample test: Product photography
81.5 rank points · Rank 5 of 28
Sample: 1 · Data date: August 18, 2026
1.GPT Image 295.1 rank points
3.MAI-Image-2.586.4 rank points
4.Nano Banana Pro82.7 rank points
5.Krea 2 Large, Current model81.5 rank points
5.Nano Banana 2 Lite81.5 rank points
7.HunyuanImage 3.0 Instruct76.6 rank points
28.Stable Diffusion 3.5 Large3.7 rank points
7 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
Gradually sample test: Character and detail
32.1 rank points · Rank 19 of 28
Sample: 1 · Data date: August 18, 2026
1.MAI-Image-2.5 Flash86.4 rank points
16.Midjourney V8.143.2 rank points
18.FLUX.2 Flex39.5 rank points
19.Krea 2 Large, Current model32.1 rank points
19.Reve 2.132.1 rank points
21.HiDream-O1-Image27.1 rank points
28.Stable Diffusion 3.5 Large3.7 rank points
7 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
Gradually sample test: Infographic
93.8 rank points · Rank 3 of 28
Sample: 1 · Data date: August 18, 2026
1.Reve 2.197.5 rank points
1.Seedream 5.0 Pro97.5 rank points
3.Krea 2 Large, Current model93.8 rank points
4.Ideogram 4.086.4 rank points
5.Krea 2 Medium Turbo82.7 rank points
28.Firefly Image Model 51.2 rank points
6 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
Profile
Specifications and access
Published information about this model. Unknown values are not estimated.
Pricing
Published prices
Prices remain tied to their documented unit and source.
Measurements
Other published benchmarks
The stored dataset does not contain an exactly matching comparison cohort for these values.
LMArena Text to Image: Art
1,114.44 points
Rank 45 · 3,839 samples · Retrieved August 26, 2026
LMArenaLMArena Text to Image: Cartoon
1,110.52 points
Rank 45 · 10,101 samples · Retrieved August 26, 2026
LMArenaLMArena Text to Image: Commercial design
1,102.41 points
Rank 50 · 9,705 samples · Retrieved August 26, 2026
LMArenaLMArena Text to Image: Overall
1,104.94 points
Rank 48 · 26,191 samples · Retrieved August 26, 2026
LMArenaLMArena Text to Image: Photorealism
1,119.79 points
Rank 44 · 10,259 samples · Retrieved August 26, 2026
LMArenaLMArena Text to Image: Portraits
1,116.15 points
Rank 47 · 4,877 samples · Retrieved August 26, 2026
LMArenaLMArena Text to Image: Text rendering
1,108.99 points
Rank 48 · 8,849 samples · Retrieved August 26, 2026
LMArenaHead-to-head comparisons
Compare this model
Each matchup compares this model with exactly one other model from the same category.
More models
Models from the same selection
All AI models
Evidence
Primary sources and data date
Every statement links to its underlying documentation or leaderboard.