Image modelPreview

Nano Banana 2

Google

Released: February 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 20 of 28
Index score: 46 / 100
Coverage: 4 / 4

Leaderboard

1MAI-Image-2.5 Flash76.6 / 100

2GPT Image 271 / 100

3MAI-Image-2.567.6 / 100

18FLUX.2 Pro47.2 / 100

20Nano Banana 246 / 100

21Wan 2.6 Text to Image39.2 / 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.

Text to Image Arena

1,321 Elo · Rank 3 of 25

Sample: 15,335 · Data date: August 26, 2026

1.GPT Image 21,371 Elo

2.Reve 2.11,322 Elo

3.Nano Banana 21,321 Elo

4.GPT Image 1.51,310 Elo

5.MAI-Image-2.51,303 Elo

25.FLUX.2 Klein 9B1,144 Elo

6 of 25 model versions shown in this chart. A higher value ranks first.

Source: Artificial AnalysisParticipants: 25

Image Editing Arena

1,250 Elo · Rank 5 of 19

Sample: 12,690 · Data date: August 26, 2026

1.Reve 2.11,263 Elo

2.MAI-Image-2.51,257 Elo

4.GPT Image 1.51,251 Elo

5.Nano Banana 21,250 Elo

6.Seedream 5.0 Pro1,248 Elo

7.Nano Banana Pro1,246 Elo

19.FLUX.2 Flex1,162 Elo

7 of 19 model versions shown in this chart. A higher value ranks first.

Source: Artificial AnalysisParticipants: 19

GenExam Mathematics, strict

56.3% · Rank 1 of 6

Sample: 151 · Data date: August 26, 2026

1.Nano Banana 256.3%

2.Nano Banana Pro55.6%

3.GPT Image 250.3%

4.GPT Image 1.526.5%

5.FLUX.2 Max6.6%

6.Seedream 4.02.6%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Physics, strict

74.3% · Rank 3 of 6

Sample: 113 · Data date: August 26, 2026

1.GPT Image 279.6%

2.Nano Banana Pro75.2%

3.Nano Banana 274.3%

4.GPT Image 1.546%

5.FLUX.2 Max8.8%

6.Seedream 4.03.5%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Chemistry, strict

52.5% · Rank 3 of 6

Sample: 118 · Data date: August 26, 2026

1.GPT Image 269.5%

2.Nano Banana Pro60.2%

3.Nano Banana 252.5%

4.GPT Image 1.539%

5.FLUX.2 Max6.8%

6.Seedream 4.05.9%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Biology, strict

66% · Rank 3 of 6

Sample: 156 · Data date: August 26, 2026

1.GPT Image 289.1%

2.Nano Banana Pro75.6%

3.Nano Banana 266%

4.GPT Image 1.556.4%

5.Seedream 4.018.6%

6.FLUX.2 Max11.6%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Geography, strict

69.7% · Rank 3 of 6

Sample: 66 · Data date: August 26, 2026

1.GPT Image 284.8%

2.Nano Banana Pro75.8%

3.Nano Banana 269.7%

4.GPT Image 1.560.6%

5.FLUX.2 Max15.2%

6.Seedream 4.010.6%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Computer science, strict

56.9% · Rank 3 of 6

Sample: 102 · Data date: August 26, 2026

1.GPT Image 273.5%

2.Nano Banana Pro65.7%

3.Nano Banana 256.9%

4.GPT Image 1.536.3%

5.FLUX.2 Max8.8%

6.Seedream 4.06.9%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Engineering, strict

67.6% · Rank 3 of 6

Sample: 111 · Data date: August 26, 2026

1.GPT Image 279.3%

2.Nano Banana Pro71.2%

3.Nano Banana 267.6%

4.GPT Image 1.544.1%

5.Seedream 4.011.7%

6.FLUX.2 Max10.8%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Economics, strict

63.6% · Rank 3 of 6

Sample: 77 · Data date: August 26, 2026

1.Nano Banana Pro88.3%

2.GPT Image 283.1%

3.Nano Banana 263.6%

4.GPT Image 1.542.9%

5.Seedream 4.05.2%

6.FLUX.2 Max2.6%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Music, strict

50.8% · Rank 3 of 6

Sample: 65 · Data date: August 26, 2026

1.GPT Image 264.6%

2.Nano Banana Pro61.5%

3.Nano Banana 250.8%

4.GPT Image 1.529.2%

5.FLUX.2 Max6.2%

6.Seedream 4.00%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam History, strict

82.9% · Rank 2 of 6

Sample: 41 · Data date: August 26, 2026

1.Nano Banana Pro97.6%

2.GPT Image 282.9%

2.Nano Banana 282.9%

4.GPT Image 1.551.2%

5.FLUX.2 Max7.3%

5.Seedream 4.07.3%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam overall, strict

64.1% · Rank 3 of 6

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

1.GPT Image 274.6%

2.Nano Banana Pro72.7%

3.Nano Banana 264.1%

4.GPT Image 1.543.2%

5.FLUX.2 Max8.5%

6.Seedream 4.07.2%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Mathematics, relaxed

87.8% · Rank 1 of 6

Sample: 151 · Data date: August 26, 2026

1.Nano Banana 287.8%

2.Nano Banana Pro86.3%

3.GPT Image 285.2%

4.GPT Image 1.565.8%

5.FLUX.2 Max49.1%

6.Seedream 4.039.8%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Physics, relaxed

95.7% · Rank 1 of 6

Sample: 113 · Data date: August 26, 2026

1.Nano Banana 295.7%

2.GPT Image 295.6%

3.Nano Banana Pro95.1%

4.GPT Image 1.585.4%

5.FLUX.2 Max63.2%

6.Seedream 4.049%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Chemistry, relaxed

90% · Rank 2 of 6

Sample: 118 · Data date: August 26, 2026

1.GPT Image 292%

2.Nano Banana 290%

3.Nano Banana Pro88.7%

4.GPT Image 1.578.1%

5.FLUX.2 Max54%

6.Seedream 4.046.1%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Biology, relaxed

95.2% · Rank 3 of 6

Sample: 156 · Data date: August 26, 2026

1.GPT Image 297.5%

2.Nano Banana Pro95.9%

3.Nano Banana 295.2%

4.GPT Image 1.591.9%

5.FLUX.2 Max74.5%

6.Seedream 4.071%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Geography, relaxed

94.8% · Rank 3 of 6

Sample: 66 · Data date: August 26, 2026

1.GPT Image 297.6%

2.Nano Banana Pro96.5%

3.Nano Banana 294.8%

4.GPT Image 1.592.5%

5.FLUX.2 Max76.3%

6.Seedream 4.065.1%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Computer science, relaxed

88.8% · Rank 3 of 6

Sample: 102 · Data date: August 26, 2026

1.GPT Image 293.3%

2.Nano Banana Pro91.7%

3.Nano Banana 288.8%

4.GPT Image 1.575.8%

5.FLUX.2 Max56.5%

6.Seedream 4.052.2%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Engineering, relaxed

95.8% · Rank 2 of 6

Sample: 111 · Data date: August 26, 2026

1.GPT Image 296.5%

2.Nano Banana 295.8%

3.Nano Banana Pro95.1%

4.GPT Image 1.586.4%

5.FLUX.2 Max68.9%

6.Seedream 4.060%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Economics, relaxed

94.2% · Rank 3 of 6

Sample: 77 · Data date: August 26, 2026

1.GPT Image 297.7%

2.Nano Banana Pro97.2%

3.Nano Banana 294.2%

4.GPT Image 1.585.5%

5.FLUX.2 Max61.5%

6.Seedream 4.056%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam Music, relaxed

86.9% · Rank 3 of 6

Sample: 65 · Data date: August 26, 2026

1.Nano Banana Pro91%

2.GPT Image 289.1%

3.Nano Banana 286.9%

4.GPT Image 1.570.8%

5.FLUX.2 Max47%

6.Seedream 4.034.5%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam History, relaxed

97.3% · Rank 2 of 6

Sample: 41 · Data date: August 26, 2026

1.Nano Banana Pro99.9%

2.Nano Banana 297.3%

3.GPT Image 297.1%

4.GPT Image 1.590.9%

5.FLUX.2 Max68%

6.Seedream 4.056.7%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

GenExam overall, relaxed

92.6% · Rank 3 of 6

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

1.GPT Image 293.8%

2.Nano Banana Pro93.7%

3.Nano Banana 292.6%

4.GPT Image 1.582.3%

5.FLUX.2 Max61.9%

6.Seedream 4.053%

6 of 6 model versions shown in this chart. A higher value ranks first.

1,000 multidisciplinary drawing tasks with reference images and fine-grained scoring points. Strict and relaxed scoring remain separate.

Source: GenExamParticipants: 6

Qwen Image Bench quality

54.77 points · Rank 4 of 5

Data date: August 26, 2026

1.GPT Image 258.65 points

2.Nano Banana Pro55.67 points

3.GPT Image 1.555.14 points

4.Nano Banana 254.77 points

5.Qwen Image 2.0 Pro54.39 points

5 of 5 model versions shown in this chart. A higher value ranks first.

1,000 prompts, five top-level dimensions, and 56 detailed facets. Published top-five scores use the same deterministic judge configuration.

Source: Qwen Image BenchParticipants: 5

Qwen Image Bench aesthetics

61.08 points · Rank 2 of 5

Data date: August 26, 2026

1.GPT Image 267.53 points

2.Nano Banana 261.08 points

3.GPT Image 1.560.88 points

4.Nano Banana Pro60.26 points

5.Qwen Image 2.0 Pro58.67 points

5 of 5 model versions shown in this chart. A higher value ranks first.

1,000 prompts, five top-level dimensions, and 56 detailed facets. Published top-five scores use the same deterministic judge configuration.

Source: Qwen Image BenchParticipants: 5

Qwen Image Bench alignment

62.4 points · Rank 2 of 5

Data date: August 26, 2026

1.GPT Image 265.85 points

2.Nano Banana 262.4 points

3.GPT Image 1.561.72 points

4.Nano Banana Pro61.25 points

5.Qwen Image 2.0 Pro59.28 points

5 of 5 model versions shown in this chart. A higher value ranks first.

1,000 prompts, five top-level dimensions, and 56 detailed facets. Published top-five scores use the same deterministic judge configuration.

Source: Qwen Image BenchParticipants: 5

Qwen Image Bench real-world fidelity

54.28 points · Rank 2 of 5

Data date: August 26, 2026

1.GPT Image 257.38 points

2.Nano Banana 254.28 points

3.Nano Banana Pro54.07 points

4.GPT Image 1.553.95 points

5.Qwen Image 2.0 Pro51.83 points

5 of 5 model versions shown in this chart. A higher value ranks first.

1,000 prompts, five top-level dimensions, and 56 detailed facets. Published top-five scores use the same deterministic judge configuration.

Source: Qwen Image BenchParticipants: 5

Qwen Image Bench creative generation

67.05 points · Rank 2 of 5

Data date: August 26, 2026

1.GPT Image 275.23 points

2.Nano Banana 267.05 points

3.GPT Image 1.566.35 points

4.Nano Banana Pro66.23 points

5.Qwen Image 2.0 Pro64.94 points

5 of 5 model versions shown in this chart. A higher value ranks first.

1,000 prompts, five top-level dimensions, and 56 detailed facets. Published top-five scores use the same deterministic judge configuration.

Source: Qwen Image BenchParticipants: 5

Qwen Image Bench overall

59.82 points · Rank 2 of 5

Data date: August 26, 2026

1.GPT Image 264.69 points

2.Nano Banana 259.82 points

3.GPT Image 1.559.65 points

4.Nano Banana Pro59.45 points

5.Qwen Image 2.0 Pro57.84 points

5 of 5 model versions shown in this chart. A higher value ranks first.

1,000 prompts, five top-level dimensions, and 56 detailed facets. Published top-five scores use the same deterministic judge configuration.

Source: Qwen Image BenchParticipants: 5

GRADE reasoning

72.6 points · Rank 3 of 7

Sample: 520 · Data date: August 26, 2026

1.GPT Image 282.2 points

2.Nano Banana Pro77.5 points

3.Nano Banana 272.6 points

4.GPT Image 1.554.5 points

5.FLUX.2 Max47.8 points

6.FLUX.2 Pro38.9 points

7.Seedream 4.032.4 points

7 of 7 model versions shown in this chart. A higher value ranks first.

520 scientific image-editing tasks across ten academic domains. GRADE scores reasoning, consistency, readability, and domain accuracy separately.

Source: GRADEParticipants: 7

GRADE consistency

86.4 points · Rank 3 of 7

Sample: 520 · Data date: August 26, 2026

1.GPT Image 294.4 points

2.Nano Banana Pro89.5 points

3.Nano Banana 286.4 points

4.GPT Image 1.582.3 points

5.FLUX.2 Max67.2 points

6.FLUX.2 Pro55.5 points

7.Seedream 4.053.2 points

7 of 7 model versions shown in this chart. A higher value ranks first.

520 scientific image-editing tasks across ten academic domains. GRADE scores reasoning, consistency, readability, and domain accuracy separately.

Source: GRADEParticipants: 7

GRADE readability

95.9 points · Rank 2 of 7

Sample: 520 · Data date: August 26, 2026

1.GPT Image 298.8 points

2.Nano Banana 295.9 points

3.Nano Banana Pro95.8 points

4.GPT Image 1.590.7 points

5.Seedream 4.077 points

6.FLUX.2 Pro70.3 points

7.FLUX.2 Max68.6 points

7 of 7 model versions shown in this chart. A higher value ranks first.

520 scientific image-editing tasks across ten academic domains. GRADE scores reasoning, consistency, readability, and domain accuracy separately.

Source: GRADEParticipants: 7

GRADE accuracy

39.6 points · Rank 3 of 7

Sample: 520 · Data date: August 26, 2026

1.GPT Image 256 points

2.Nano Banana Pro46.2 points

3.Nano Banana 239.6 points

4.GPT Image 1.516 points

5.FLUX.2 Max11.9 points

6.FLUX.2 Pro4.4 points

7.Seedream 4.03.1 points

7 of 7 model versions shown in this chart. A higher value ranks first.

520 scientific image-editing tasks across ten academic domains. GRADE scores reasoning, consistency, readability, and domain accuracy separately.

Source: GRADEParticipants: 7

GenAI-Bench overall preference

1,073 Elo · Rank 1 of 3

Data date: August 26, 2026

1.Nano Banana 21,073 Elo

2.GPT Image 1.51,047 Elo

3.Nano Banana Pro1,021 Elo

3 of 3 model versions shown in this chart. A higher value ranks first.

Google's model card reports Elo scores with uncertainty intervals for text-to-image generation and image editing. These rows use standard Gemini 3.1 Flash Image without tools.

Source: Gemini 3.1 Flash Image model cardParticipants: 3

GenAI-Bench visual quality

1,129 Elo · Rank 1 of 3

Data date: August 26, 2026

1.Nano Banana 21,129 Elo

2.Nano Banana Pro1,043 Elo

3.GPT Image 1.5975 Elo

3 of 3 model versions shown in this chart. A higher value ranks first.

Google's model card reports Elo scores with uncertainty intervals for text-to-image generation and image editing. These rows use standard Gemini 3.1 Flash Image without tools.

Source: Gemini 3.1 Flash Image model cardParticipants: 3

Infographics factuality

1,074 Elo · Rank 2 of 3

Data date: August 26, 2026

1.Nano Banana Pro1,102 Elo

2.Nano Banana 21,074 Elo

3.GPT Image 1.5985 Elo

3 of 3 model versions shown in this chart. A higher value ranks first.

Google's model card reports Elo scores with uncertainty intervals for text-to-image generation and image editing. These rows use standard Gemini 3.1 Flash Image without tools.

Source: Gemini 3.1 Flash Image model cardParticipants: 3

General image editing

1,047 Elo · Rank 2 of 3

Data date: August 26, 2026

1.Nano Banana Pro1,051 Elo

2.Nano Banana 21,047 Elo

3.GPT Image 1.5995 Elo

3 of 3 model versions shown in this chart. A higher value ranks first.

Google's model card reports Elo scores with uncertainty intervals for text-to-image generation and image editing. These rows use standard Gemini 3.1 Flash Image without tools.

Source: Gemini 3.1 Flash Image model cardParticipants: 3

Character editing

1,049 Elo · Rank 2 of 3

Data date: August 26, 2026

1.Nano Banana Pro1,050 Elo

2.Nano Banana 21,049 Elo

3.GPT Image 1.51,025 Elo

3 of 3 model versions shown in this chart. A higher value ranks first.

Google's model card reports Elo scores with uncertainty intervals for text-to-image generation and image editing. These rows use standard Gemini 3.1 Flash Image without tools.

Source: Gemini 3.1 Flash Image model cardParticipants: 3

Creative editing

1,031 Elo · Rank 1 of 3

Data date: August 26, 2026

1.Nano Banana 21,031 Elo

2.GPT Image 1.51,017 Elo

3.Nano Banana Pro1,004 Elo

3 of 3 model versions shown in this chart. A higher value ranks first.

Google's model card reports Elo scores with uncertainty intervals for text-to-image generation and image editing. These rows use standard Gemini 3.1 Flash Image without tools.

Source: Gemini 3.1 Flash Image model cardParticipants: 3

Object and environment editing

1,018 Elo · Rank 2 of 3

Data date: August 26, 2026

1.Nano Banana Pro1,042 Elo

2.Nano Banana 21,018 Elo

3.GPT Image 1.5976 Elo

3 of 3 model versions shown in this chart. A higher value ranks first.

Google's model card reports Elo scores with uncertainty intervals for text-to-image generation and image editing. These rows use standard Gemini 3.1 Flash Image without tools.

Source: Gemini 3.1 Flash Image model cardParticipants: 3

Editing with 1-3 input images

1,016 Elo · Rank 2 of 3

Data date: August 26, 2026

1.Nano Banana Pro1,056 Elo

2.Nano Banana 21,016 Elo

3.GPT Image 1.51,014 Elo

3 of 3 model versions shown in this chart. A higher value ranks first.

Google's model card reports Elo scores with uncertainty intervals for text-to-image generation and image editing. These rows use standard Gemini 3.1 Flash Image without tools.

Source: Gemini 3.1 Flash Image model cardParticipants: 3

Stylization

1,031 Elo · Rank 2 of 3

Data date: August 26, 2026

1.Nano Banana Pro1,045 Elo

2.Nano Banana 21,031 Elo

3.GPT Image 1.5996 Elo

3 of 3 model versions shown in this chart. A higher value ranks first.

Google's model card reports Elo scores with uncertainty intervals for text-to-image generation and image editing. These rows use standard Gemini 3.1 Flash Image without tools.

Source: Gemini 3.1 Flash Image model cardParticipants: 3

ContraLabs typography, first-place wins

30% · Rank 2 of 3

Data date: August 26, 2026

1.Ideogram 4.047.9%

2.Nano Banana 230%

3.FLUX.2 Max15.5%

3 of 3 model versions shown in this chart. A higher value ranks first.

A blind typography test by ContraLabs. The provider's model card reports the first-place win rate from ten professional designers.

Source: ContraLabs via Ideogram 4 model cardParticipants: 3

ContraLabs client-work suitability

2.84 rating out of 5 · Rank 2 of 3

Data date: August 26, 2026

1.Ideogram 4.03.55 rating out of 5

2.Nano Banana 22.84 rating out of 5

3.FLUX.2 Max2.49 rating out of 5

3 of 3 model versions shown in this chart. A higher value ranks first.

A blind typography test by ContraLabs. Ten professional designers rated on a 1-to-5 scale whether they would use the output in real client work.

Source: ContraLabs via Ideogram 4 model cardParticipants: 3

Gradually sample test: Typography and layout

86.4 rank points · Rank 4 of 28

Sample: 1 · Data date: August 18, 2026

1.MAI-Image-2.593.8 rank points

1.Nano Banana Pro93.8 rank points

3.Recraft V4.1 Utility92.6 rank points

4.Nano Banana 286.4 rank points

5.FLUX.2 Max85.2 rank points

6.Nano Banana 2 Lite81.5 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

29.6 rank points · Rank 20 of 28

Sample: 1 · Data date: August 18, 2026

1.GPT Image 295.1 rank points

18.Midjourney V8.140.7 rank points

19.GPT Image 1.537 rank points

20.Nano Banana 229.6 rank points

21.Wan 2.6 Text to Image25.9 rank points

22.Recraft V4.1 Utility22.2 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.

Source: Gradually-BildtestParticipants: 28

Gradually sample test: Character and detail

18.5 rank points · Rank 25 of 28

Sample: 1 · Data date: August 18, 2026

1.MAI-Image-2.5 Flash86.4 rank points

23.MAI-Image-2.524.7 rank points

24.Nano Banana Pro21 rank points

25.Nano Banana 218.5 rank points

26.Nano Banana 2 Lite17.3 rank points

27.Seedream 4.013.6 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.

Source: Gradually-BildtestParticipants: 28

Gradually sample test: Infographic

49.4 rank points · Rank 14 of 28

Sample: 1 · Data date: August 18, 2026

1.Reve 2.197.5 rank points

13.Qwen Image 2.0 Pro53.1 rank points

14.GPT Image 1.549.4 rank points

14.Nano Banana 249.4 rank points

14.Wan 2.6 Text to Image49.4 rank points

17.Nano Banana Pro42 rank points

28.Firefly Image Model 51.2 rank points

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

Source: Gradually-BildtestParticipants: 28

Profile

Specifications and access

Published information about this model. Unknown values are not estimated.

Weights: ProprietarySource
Access: API, WebSource
Maximum output: 4KSource
Benchmark configuration: Gemini 3.1 Flash Image PreviewSource
Generator: gemini-3.1-flash-imageSource

Pricing

Published prices

Prices remain tied to their documented unit and source.

Representative price: $0.07 per imageSource
Together AI (google/flash-image-3.1): $0.05 per imageSource

Measurements

Other published benchmarks

The stored dataset does not contain an exactly matching comparison cohort for these values.

LMArena Text to Image: 3D modeling

1,258.7 points

Rank 3 · 2,907 samples · Retrieved August 26, 2026

LMArena

LMArena Text to Image: Art

1,250.51 points

Rank 8 · 4,154 samples · Retrieved August 26, 2026

LMArena

LMArena Text to Image: Cartoon

1,266.73 points

Rank 8 · 10,445 samples · Retrieved August 26, 2026

LMArena

LMArena Text to Image: Commercial design

1,272.16 points

Rank 4 · 10,316 samples · Retrieved August 26, 2026

LMArena

LMArena Text to Image: Overall

1,263.06 points

Rank 5 · 27,910 samples · Retrieved August 26, 2026

LMArena

LMArena Text to Image: Photorealism

1,269.81 points

Rank 6 · 11,229 samples · Retrieved August 26, 2026

LMArena

LMArena Text to Image: Portraits

1,266.8 points

Rank 7 · 5,554 samples · Retrieved August 26, 2026

LMArena

LMArena Text to Image: Text rendering

1,294.78 points

Rank 5 · 9,489 samples · Retrieved August 26, 2026

LMArena

LMArena Image Editing: Multi-image editing

1,364.76 points

Rank 5 · 37,577 samples · Retrieved August 26, 2026

LMArena

LMArena Image Editing: Overall

1,386.27 points

Rank 10 · 117,943 samples · Retrieved August 26, 2026

LMArena

Head-to-head comparisons

Compare this model

Each matchup compares this model with exactly one other model from the same category.

Nano Banana 2 vs. GPT Image 2

Nano Banana 2 vs. Reve 2.1

Nano Banana 2 vs. GPT Image 1.5

Nano Banana 2 vs. MAI-Image-2.5

Nano Banana 2 vs. Nano Banana Pro

Nano Banana 2 vs. Nano Banana 2 Lite

Nano Banana 2 vs. Seedream 5.0 Pro

Nano Banana 2 vs. Grok Imagine Image Quality

Nano Banana 2 vs. FLUX.2 Max

Nano Banana 2 vs. Qwen Image 2.0 Pro

Nano Banana 2 vs. MAI-Image-2.5 Flash

Nano Banana 2 vs. HiDream-O1-Image-1.5

Nano Banana 2 vs. Krea 2 Medium Turbo

Nano Banana 2 vs. Seedream 4.0

Nano Banana 2 vs. Krea 2 Large

Nano Banana 2 vs. Luma UNI 1 Max

Nano Banana 2 vs. FLUX.2 Flex

Nano Banana 2 vs. Recraft V4.1 Utility

Nano Banana 2 vs. Ideogram 4.0

Nano Banana 2 vs. Wan 2.6 Text to Image

Nano Banana 2 vs. FLUX.2 Pro

Nano Banana 2 vs. HunyuanImage 3.0 Instruct

Nano Banana 2 vs. FLUX.2 Klein 9B

Nano Banana 2 vs. HiDream-O1-Image

Nano Banana 2 vs. Firefly Image Model 5

Nano Banana 2 vs. Midjourney V8.1

Nano Banana 2 vs. Stable Diffusion 3.5 Large

More models

Models from the same selection

All AI models

Reve 2.1

Reve

GPT Image 1.5

OpenAI

Evidence

Primary sources and data date

Every statement links to its underlying documentation or leaderboard.

GoogleSource
Image pricingSource
Lifecycle dataSource
Together AISource
Artificial Analysis (retrieved August 26, 2026)Source
LMArena (retrieved August 26, 2026)Source
LMArena (retrieved August 26, 2026)Source
GenExam (retrieved August 26, 2026)Source
Qwen Image Bench (retrieved August 26, 2026)Source
GRADE (retrieved August 26, 2026)Source
Gemini 3.1 Flash Image model card (retrieved August 26, 2026)Source
ContraLabs via Ideogram 4 model card (retrieved August 26, 2026)Source
Gradually-Bildtest (retrieved August 18, 2026)Source