Skip to content
IFAI

Model rankings

866 models · 5 boards · 2 sources

Artificial AnalysisText-to-image arenaArenaText-to-image arena

Text-to-image arena · Anonymous head-to-head votes · Updated November 3, 2026

Best images
Best open model
Qwen-Image-2.1Alibaba1,043Score
Best from China
Seedream 5.0 ProByteDance Seed1,101Score
Top three by Score
3GPT Image 2 (high)OpenAI1,189
Top three open models
1Qwen-Image-2.1Alibaba · #21 overall1,043
2FLUX 3 Image KleinBlack Forest Labs · #22 overall1,043
3Fibo 2.0Bria · #23 overall1,040
This week's changes
Gemini 4 Carbon (High)Intelligence · #1New
GPT-6.1 Terra (Max)Intelligence · #6New
Fish Audio Drama 3Speech · #6New
P-Video-2-ProVideo · #11New
AssemblyAI-TTS-1Speech · #14New
RankChangeModelScore95% interval
1—GPT Image 2.5 Sunburst (max)ClosedOpenAI1,223±10
2—GPT Image 2.5 Flare (max)ClosedOpenAI1,207±10
3—GPT Image 2 (high)ClosedOpenAI1,189±11
4—Nano Banana 2.1ClosedGoogle1,176±12
5▲ 1Grok Imagine Image 2.0ClosedSpaceXAI1,168±12
6▼ 1MAI-Image-2.6ClosedMicrosoft AI1,167±12
7—Nano Banana 2 (Gemini 3.1 Flash Image)ClosedGoogle1,140±10
8—Muse ImageClosedMeta1,127±11
9—GPT Image 1.5 (high)ClosedOpenAI1,123±11
10—MAI-Image-2.6-FlashClosedMicrosoft AI1,120±12
11▲ 2FLUX 3 ImageClosedBlack Forest Labs1,119±12
12▼ 1MAI-Image-2.5ClosedMicrosoft AI1,118±11
13▼ 2Nano Banana Pro (Gemini 3 Pro Image)ClosedGoogle1,118±10
14—MAI-Image-2.5-ProClosedMicrosoft AI1,114±10
15—Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)ClosedGoogle1,107±10
16—Seedream 5.0 ProClosedByteDance Seed1,101±11
17—Qwen-Image-3.0-ProClosedAlibaba1,097±12
18—Qwen-Image-3.0ClosedAlibaba1,072±12
19—Qwen-Image-2.1-ProClosedAlibaba1,058±12
20—grok-imagine-image-qualityClosedSpaceXAI1,049±9
21—Krea 2 LargeClosedKrea1,034±9
22—Qwen Image 2.0 Pro (2026-04-22)ClosedAlibaba1,030±11
23—MAI-Image-2.5-FlashClosedMicrosoft AI1,029±11
24—Qwen-Image-2.1-TurboClosedAlibaba1,028±12
25▲ 2Seedream 4.5ClosedByteDance Seed1,027±12
26▼ 1Wan 2.6 ImageClosedAlibaba1,026±12
27▲ 1FLUX.2 [flex]ClosedBlack Forest Labs1,026±11
28▼ 2Recraft V4.1 UtilityClosedRecraft1,026±11
29—Luma UNI 1 MaxClosedLuma Labs1,024±12
30—grok-imagine-imageClosedSpaceXAI1,022±11
31—FLUX.2 [max]ClosedBlack Forest Labs1,021±10
32—Krea 2 Medium TurboClosedKrea1,021±11
33▲ 2Seedream 5.0 LiteClosedByteDance Seed1,019±12
34▼ 1Recraft V4.1 Utility ProClosedRecraft1,018±9
35▼ 1HiDream-O1-Image-1.5ClosedHiDream1,017±11
36—Ideogram 4.5 (High)ClosedIdeogram1,016±15
37—Wan2.6 Text to ImageClosedAlibaba1,015±12
38—GPT Image 1 (high)ClosedOpenAI1,014±12
39—Krea 2 MediumClosedKrea1,012±9
40—FLUX.2 [pro]ClosedBlack Forest Labs1,003±10
41—P-Image-Ideogram (High)ClosedPruna AI997±14
42—Luma UNI 1ClosedLuma Labs993±12
43—P-Image-Ideogram (Very High)ClosedPruna AI992±15
44—Qwen Image 2.0 (2026-03-03)ClosedAlibaba990±16
45—HunyuanImage 3.0 (Tencent Cloud)ClosedTencent988±16
46—Wan 2.7ClosedAlibaba987±12
47—Nano Banana (Gemini 2.5 Flash Image)ClosedGoogle985±12
48—Wan 2.7 ProClosedAlibaba979±12
49—P-Image-Ideogram (Medium)ClosedPruna AI974±14
50—HunyuanImage 3.5 (Preview)ClosedTencent970±12

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi

Arena data comes from the leaderboard dataset it publishes on Hugging Face (CC BY 4.0). Only each board's overall leaderboard is used; scores and ranks are unchanged. dataset · CC BY 4.0

Artificial Analysis data comes from its API (artificialanalysis.ai). Scores are unchanged; ranks follow the scores. artificialanalysis.ai

Open or closed follows the license Arena gives; prices and Artificial Analysis intelligence show only where model names match, otherwise “—”.