Head-to-head comparison

Nano Banana 2 vs. Nano Banana Pro

Compare shared capability tests, arena scores with documented retrieval dates, task-specific image pricing, and verified specifications. Research benchmarks, preference arenas, and our n = 1 samples remain separate.

shared result series: 57
shared sample prompts: 4
latest arena retrieval: 2026-08-26

First image modelSecond image model

Specifications and cost

General specifications and task-specific pricing

A model can have one price for generating new images and another for editing. Prices therefore remain tied to the corresponding arena configuration.

Specifications and pricing for Nano Banana 2 and Nano Banana Pro
Attribute	Nano Banana 2	Nano Banana Pro
Provider	Google	Google
Released	February 2026	November 2025
Access	API, Web app	API, Web app
Lifecycle	Stable API since May 28, 2026. The arena entry names the earlier preview configuration Status source	No separate lifecycle notice
Weights	Proprietary	Proprietary
Parameters	Not published	Not published
Maximum output	4K	4K
Arena configuration	Gemini 3.1 Flash Image Preview	Gemini 3 Pro Image
Text-to-image price	$67 per 1,000 images	$134 per 1,000 images
Editing price	$67 per 1,000 images	$134 per 1,000 images
Technical source	Model sourceVerified 2026-08-15	Model sourceVerified 2026-08-15

Nano Banana 2Nano Banana Pro

Text to Image ArenaUSD per 1,000 images at 1,024 × 1,024 pixels

Nano Banana 2$67

Nano Banana Pro$134

Image Editing ArenaUSD per 1,000 images at 1,024 × 1,024 pixels

Nano Banana 2$67

Nano Banana Pro$134

Key to the marks:better valuebetter, but not conclusivetie

Prompt adherence and specialist tests

Shared capability benchmarks

Every matchup includes the same four Gradually sample tasks. For each task, one archived first output from every model is ranked in three differently ordered, model-blind passes. The published 0-100 value normalizes the mean rank. It must still be read as an n = 1 sample per model. This pair also shares 41 results from published research benchmarks.

Nano Banana 2Nano Banana Pro

Gradually sample test: Typography and layoutMean of three blind ranks across all 28 first outputs, n = 1 each

Nano Banana 286.4 / 100

Nano Banana Pro93.8 / 100

Gradually sample test: Product photographyMean of three blind ranks across all 28 first outputs, n = 1 each

Nano Banana 229.6 / 100

Nano Banana Pro82.7 / 100

Gradually sample test: Character and detailMean of three blind ranks across all 28 first outputs, n = 1 each

Nano Banana 218.5 / 100

Nano Banana Pro21 / 100

Gradually sample test: InfographicMean of three blind ranks across all 28 first outputs, n = 1 each

Nano Banana 249.4 / 100

Nano Banana Pro42 / 100

Key to the marks:better valuebetter, but not conclusivetie

Capability benchmark scores for Nano Banana 2 and Nano Banana Pro
Benchmark	Nano Banana 2	Nano Banana Pro
GenExam Mathematics, strict	Higher benchmark score56.3 %	55.6 %
GenExam Physics, strict	74.3 %	Higher benchmark score75.2 %
GenExam Chemistry, strict	52.5 %	Higher benchmark score60.2 %
GenExam Biology, strict	66 %	Higher benchmark score75.6 %
GenExam Geography, strict	69.7 %	Higher benchmark score75.8 %
GenExam Computer science, strict	56.9 %	Higher benchmark score65.7 %
GenExam Engineering, strict	67.6 %	Higher benchmark score71.2 %
GenExam Economics, strict	63.6 %	Higher benchmark score88.3 %
GenExam Music, strict	50.8 %	Higher benchmark score61.5 %
GenExam History, strict	82.9 %	Higher benchmark score97.6 %
GenExam overall, strict	64.1 %	Higher benchmark score72.7 %
GenExam Mathematics, relaxed	Higher benchmark score87.8 %	86.3 %
GenExam Physics, relaxed	Higher benchmark score95.7 %	95.1 %
GenExam Chemistry, relaxed	Higher benchmark score90 %	88.7 %
GenExam Biology, relaxed	95.2 %	Higher benchmark score95.9 %
GenExam Geography, relaxed	94.8 %	Higher benchmark score96.5 %
GenExam Computer science, relaxed	88.8 %	Higher benchmark score91.7 %
GenExam Engineering, relaxed	Higher benchmark score95.8 %	95.1 %
GenExam Economics, relaxed	94.2 %	Higher benchmark score97.2 %
GenExam Music, relaxed	86.9 %	Higher benchmark score91 %
GenExam History, relaxed	97.3 %	Higher benchmark score99.9 %
GenExam overall, relaxed	92.6 %	Higher benchmark score93.7 %
Qwen Image Bench quality	54.77 / 100	Higher benchmark score55.67 / 100
Qwen Image Bench aesthetics	Higher benchmark score61.08 / 100	60.26 / 100
Qwen Image Bench alignment	Higher benchmark score62.4 / 100	61.25 / 100
Qwen Image Bench real-world fidelity	Higher benchmark score54.28 / 100	54.07 / 100
Qwen Image Bench creative generation	Higher benchmark score67.05 / 100	66.23 / 100
Qwen Image Bench overall	Higher benchmark score59.82 / 100	59.45 / 100
GRADE reasoning	72.6 / 100	Higher benchmark score77.5 / 100
GRADE consistency	86.4 / 100	Higher benchmark score89.5 / 100
GRADE readability	Higher benchmark score95.9 / 100	95.8 / 100
GRADE accuracy	39.6 / 100	Higher benchmark score46.2 / 100
GenAI-Bench overall preference	Higher benchmark score1,073 ± 5	1,021 ± 5
GenAI-Bench visual quality	Higher benchmark score1,129 ± 6	1,043 ± 5
Infographics factuality	1,074 ± 12	Higher benchmark score1,102 ± 13
General image editing	1,047 ± 9	No clear benchmark lead1,051 ± 10
Character editing	1,049 ± 7	No clear benchmark lead1,050 ± 8
Creative editing	Higher benchmark score1,031 ± 7	1,004 ± 7
Object and environment editing	1,018 ± 8	Higher benchmark score1,042 ± 10
Editing with 1-3 input images	1,016 ± 8	Higher benchmark score1,056 ± 12
Stylization	1,031 ± 7	No clear benchmark lead1,045 ± 9
Gradually sample test: Typography and layout	86.4 / 100 Mean rank: 4.67 (8 / 2 / 4) Five rubric scores Headline: 1.67 / 2 Subline: 1.67 / 2 Text control: 1.67 / 2 Visual brief: 1.33 / 2 Layout: 1.33 / 2	Higher blind-rank score93.8 / 100 Mean rank: 2.67 (5 / 1 / 2) Five rubric scores Headline: 1.67 / 2 Subline: 1.67 / 2 Text control: 1.67 / 2 Visual brief: 1.33 / 2 Layout: 1.33 / 2
Gradually sample test: Product photography	29.6 / 100 Mean rank: 20 (24 / 17 / 19) Five rubric scores Subject: 1.33 / 2 Time: 1.33 / 2 Watch details: 1.33 / 2 Photography: 1.33 / 2 Exclusions: 1 / 2	Higher blind-rank score82.7 / 100 Mean rank: 5.67 (7 / 8 / 2) Five rubric scores Subject: 1.33 / 2 Time: 1.33 / 2 Watch details: 1.33 / 2 Photography: 1.33 / 2 Exclusions: 1.33 / 2
Gradually sample test: Character and detail	18.5 / 100 Mean rank: 23 (24 / 18 / 27) Five rubric scores Scene: 1.33 / 2 Wardrobe: 1.33 / 2 Anatomy: 1 / 2 Props: 0.67 / 2 Environment: 0.67 / 2	Higher blind-rank score21 / 100 Mean rank: 22.33 (20 / 24 / 23) Five rubric scores Scene: 1.33 / 2 Wardrobe: 1.33 / 2 Anatomy: 1 / 2 Props: 0.33 / 2 Environment: 1 / 2
Gradually sample test: Infographic	Higher blind-rank score49.4 / 100 Mean rank: 14.67 (16 / 14 / 14) Five rubric scores Title: 1.67 / 2 Sequence: 1 / 2 Labels: 1 / 2 Diagram: 1.67 / 2 Clarity: 1 / 2	42 / 100 Mean rank: 16.67 (17 / 16 / 17) Five rubric scores Title: 1.67 / 2 Sequence: 1.67 / 2 Labels: 1 / 2 Diagram: 1.67 / 2 Clarity: 1 / 2
Key to the marks:better valuebetter, but not conclusivetie

Independent preference tests

Shared arena benchmarks

Artificial Analysis and Arena derive scores from blind comparisons. Raters see outputs for the same prompt and choose the image they prefer. Separate series cover text rendering, photorealism, portraits, art, commercial design, and image editing. Confidence intervals indicate how certain a measured lead is.

12 shared result series

Nano Banana 2Nano Banana Pro

Text to Image ArenaBlind preference from the same prompt, higher is better

Nano Banana 21,321 Elo

Nano Banana Pro1,298 Elo

Image Editing ArenaBlind preference from the same prompt, higher is better

Nano Banana 21,250 Elo

Nano Banana Pro1,246 Elo

LMArena Text to Image: 3D modelingBlind preference from the same prompt, higher is better

Nano Banana 21,258.705

Nano Banana Pro1,230.042

LMArena Text to Image: ArtBlind preference from the same prompt, higher is better

Nano Banana 21,250.508

Nano Banana Pro1,224.748

LMArena Text to Image: CartoonBlind preference from the same prompt, higher is better

Nano Banana 21,266.735

Nano Banana Pro1,240.574

LMArena Text to Image: Commercial designBlind preference from the same prompt, higher is better

Nano Banana 21,272.164

Nano Banana Pro1,245.099

LMArena Text to Image: OverallBlind preference from the same prompt, higher is better

Nano Banana 21,263.056

Nano Banana Pro1,245.593

LMArena Text to Image: PhotorealismBlind preference from the same prompt, higher is better

Nano Banana 21,269.812

Nano Banana Pro1,260.121

LMArena Text to Image: PortraitsBlind preference from the same prompt, higher is better

Nano Banana 21,266.805

Nano Banana Pro1,258.035

LMArena Text to Image: Text renderingBlind preference from the same prompt, higher is better

Nano Banana 21,294.784

Nano Banana Pro1,269.198

LMArena Image Editing: Multi-image editingBlind preference from the same prompt, higher is better

Nano Banana 21,364.764

Nano Banana Pro1,363.811

LMArena Image Editing: OverallBlind preference from the same prompt, higher is better

Nano Banana 21,386.267

Nano Banana Pro1,389.596

Key to the marks:better valuebetter, but not conclusivetie

Arena benchmark scores for Nano Banana 2 and Nano Banana Pro
Benchmark	Nano Banana 2	Nano Banana Pro	Source
Text to Image Arena	Higher score1,321 Elo Rank 4, 95% confidence interval: ±9, 15,335 ratings	1,298 Elo Rank 7, 95% confidence interval: ±9, 13,840 ratings	Artificial AnalysisRetrieved 2026-08-26
Image Editing Arena	No clear lead1,250 Elo Rank 7, 95% confidence interval: ±7, 12,690 ratings	1,246 Elo Rank 10, 95% confidence interval: ±7, 11,029 ratings	Artificial AnalysisRetrieved 2026-08-26
LMArena Text to Image: 3D modeling	Higher score1,258.705 Rank 3, 95% confidence interval: ±11.62, 2,907 ratings	1,230.042 Rank 7, 95% confidence interval: ±7.01, 13,757 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Art	Higher score1,250.508 Rank 8, 95% confidence interval: ±9.92, 4,154 ratings	1,224.748 Rank 10, 95% confidence interval: ±6.22, 19,671 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Cartoon	Higher score1,266.735 Rank 8, 95% confidence interval: ±7.6, 10,445 ratings	1,240.574 Rank 11, 95% confidence interval: ±4.92, 56,045 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Commercial design	Higher score1,272.164 Rank 4, 95% confidence interval: ±7.4, 10,316 ratings	1,245.099 Rank 9, 95% confidence interval: ±4.81, 50,186 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Overall	Higher score1,263.056 Rank 5, 95% confidence interval: ±5.24, 27,910 ratings	1,245.593 Rank 10, 95% confidence interval: ±3.37, 138,756 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Photorealism	No clear lead1,269.812 Rank 6, 95% confidence interval: ±7.28, 11,229 ratings	1,260.121 Rank 7, 95% confidence interval: ±4.77, 59,290 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Portraits	No clear lead1,266.805 Rank 7, 95% confidence interval: ±9.15, 5,554 ratings	1,258.035 Rank 11, 95% confidence interval: ±5.76, 31,463 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Text rendering	Higher score1,294.784 Rank 5, 95% confidence interval: ±7.73, 9,489 ratings	1,269.198 Rank 9, 95% confidence interval: ±5.14, 46,529 ratings	LMArenaRetrieved 2026-08-26
LMArena Image Editing: Multi-image editing	No clear lead1,364.764 Rank 5, 95% confidence interval: ±4.86, 37,577 ratings	1,363.811 Rank 6, 95% confidence interval: ±3.91, 189,338 ratings	LMArenaRetrieved 2026-08-26
LMArena Image Editing: Overall	1,386.267 Rank 10, 95% confidence interval: ±3.71, 117,943 ratings	No clear lead1,389.596 Rank 8, 95% confidence interval: ±2.85, 517,418 ratings	LMArenaRetrieved 2026-08-26
Key to the marks:better valuebetter, but not conclusivetie

Visual comparison

Sample images

Our images complement preference data, but do not replace it. The prompt, request count, and selection rule match. Provider resolution, quality tier, randomness, and prompt processing remain visible limitations, so this is not a fully controlled laboratory test.

Largely standardized comparison protocol. Both models receive the same archived prompt, exactly one request, and the first result counts. Files are normalized to 1,024 × 1,024 pixels without cropping. Provider resolution, randomness, quality tier, and prompt processing can still differ. These images are a practical visual test, not a reconstruction of the arena configuration.

Character and detail

Anatomy, clothing, and spatial consistency

Prompt and settings

Create a square cinematic full-body portrait of a fictional bicycle courier waiting under a transparent umbrella at a rainy tram stop in Hamburg at blue hour. She wears a mustard raincoat, navy trousers, red sneakers, a silver helmet, and carries a teal messenger bag. Keep both hands visible, render the bicycle correctly, use realistic wet-street reflections, and include no readable brand names.

Nano Banana 2. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID google/flash-image-3.1, generated Aug 14, 2026, 12:15 PM. Source
Nano Banana Pro. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID google/gemini-3-pro-image, generated Aug 14, 2026, 12:20 PM. Source

Protocol gradually-image-comparison-v1, selection rule: first result.

Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6

Nano Banana 2, image SHA 256: 5d3a70ed3fe3328484725565d9c91fb25fc7f745bd66872dae432444493a83de

Nano Banana 2, request SHA 256: 406e70dda817fa504900359d5c374ebb06fc8ea29f34c8a15f630e9a10489aec

Nano Banana Pro, image SHA 256: eed53dcc080d2710e6e890382f6273382a12e2c5b079b8813962bff0c92b5df7

Nano Banana Pro, request SHA 256: 12c91e972a7256b1386b22420c0c84e30b85ac6e07830eea944755e5bd9742fc

Infographic

Numbers, labels, and visual organization

Prompt and settings

Create a square German infographic titled SO FUNKTIONIERT PHOTOSYNTHESE. Show exactly four numbered steps in this order: 1 LICHT, 2 WASSER, 3 CO₂, 4 ZUCKER + SAUERSTOFF. Use a clean editorial science style with one plant cross-section, simple arrows, high contrast, legible labels, and no other text.

Protocol gradually-image-comparison-v1, selection rule: first result.

Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f

Nano Banana 2, image SHA 256: 66123dd4e8cd5d22ecdca9cca8e4c5853a8046370aa4861ffee807a8c122c769

Nano Banana 2, request SHA 256: 10e973caab6f314ec731d9d377b19f5d51f279e9e2962133c49682bfbba3fe3d

Nano Banana Pro, image SHA 256: 4ff7d3965d18e197f00647c35d6aed5a86a376c92779ee9e748c598aebafa51d

Nano Banana Pro, request SHA 256: a69a5193f107aac4f7532f021fc4306c0907470f40f984d0b263728e292d8f1b

Product photography

Materials, reflections, and fine details

Prompt and settings

Create a square premium product photograph of a brushed titanium wristwatch standing upright on dark green marble. The watch has a cream dial, thin black hands set to 10:10, twelve distinct hour markers, a realistic crown, and a dark brown leather strap. Soft window light from the left, controlled reflections, shallow depth of field, no text, no logo, no extra objects.

Protocol gradually-image-comparison-v1, selection rule: first result.

Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3

Nano Banana 2, image SHA 256: 509871921c450f6f07ec28f91a380992db1b3017108fd5928fe0aa9670a1ecdc

Nano Banana 2, request SHA 256: 631ce921c9772c7c2109900c8662471564a871def8e70f50ce29ce83ab71daab

Nano Banana Pro, image SHA 256: d50770f426cac7920c9ffdaf210db2f11cdc51a8cf0b7ef52e6cd26850b1de70

Nano Banana Pro, request SHA 256: 92d73f9638fa47ea30f0ceefdeb5eb2ca7d4a018b4b4835463bd0ea29d0495cf

Typography and layout

Legible text, hierarchy, and composition

Prompt and settings

Create a square editorial poster for an imaginary night train called MONDFALTER. Show the exact German headline MONDFALTER and the exact subline BERLIN NACH LISSABON. Use a restrained midnight-blue and warm-cream palette, one stylized moth, strong Swiss-grid typography, generous negative space, and no additional words or logos.

Nano Banana 2. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID google/flash-image-3.1, generated Aug 14, 2026, 1:59 PM. Source
Nano Banana Pro. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID google/gemini-3-pro-image, generated Aug 14, 2026, 2:00 PM. Source

Protocol gradually-image-comparison-v1, selection rule: first result.

Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419

Nano Banana 2, image SHA 256: 06ae79c07d1604d3da3bbfa80bac73ac15c88af5cb8c013faaf5c9ea93092305

Nano Banana 2, request SHA 256: 6f1909c093d741b97bc2b4fe76e889009776dbe8635d2a14dbedd89bb4cae8fb

Nano Banana Pro, image SHA 256: fc173de00b0df04772321167cfeabb55418d3d016081e7ebfb589c69a629b712

Nano Banana Pro, request SHA 256: d686c572b086aa9f5d019886e8182c8f41c5d35bfb43bc6b6937feccba8a73eb

How to read this comparison

An Elo score is not a verdict on creativity

A higher arena score means this specific configuration was preferred more often in blind comparisons.

Typography, character consistency, local execution, licensing, and price may matter more to your workload than overall visual appeal.

Prices cover 1,000 images at 1,024 × 1,024 pixels using settings documented by Artificial Analysis. Subscriptions and special rates are excluded.

More matchups

Compare Nano Banana 2 and Nano Banana Pro with other important image models using the same benchmark and sample methodology.

View the complete image model comparison

Nano Banana 2 vs. Nano Banana Pro

Change image model selection

General specifications and task-specific pricing

Shared capability benchmarks

Shared arena benchmarks

Sample images

Character and detail

Infographic

Product photography

Typography and layout

An Elo score is not a verdict on creativity

Related image model comparisons