Skip to content
IFAI

Model rankings

1447 models · 5 boards · 2 sources

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

Text-to-image arena · Anonymous head-to-head votes · Updated August 24, 2026

Best images
GPT Image 2 (high)OpenAI1,369Score
Best open model
Ideogram 4.0Ideogram1,220Score
Best from China
Qwen-Image-3.0-ProAlibaba1,281Score
Top three by Score
1GPT Image 2 (high)OpenAI1,369
2Reve 2.1Reve1,322
Top three open models
1Ideogram 4.0Ideogram · #21 overall1,220
2FLUX.2 [dev] TurboFal · #36 overall1,200
3Ideogram 4.0 Fast (Quality)Fal · #37 overall1,200
This week's changes
hy4-previewCoding · #5New
GLM-5.3 (max)Intelligence · #6New
MAI-Image-2.5-ProImage · #7New
qwen3.8-flash-nextCoding · #8New
glm-5.3-flashCoding · #11New
RankChangeModelScore95% interval
1—GPT Image 2 (high)ClosedOpenAI1,369±10
2—Reve 2.1ClosedReve1,322±9
3—Nano Banana 2 (Gemini 3.1 Flash Image Preview)ClosedGoogle1,320±9
4—GPT Image 1.5 (high)ClosedOpenAI1,310±9
5—MAI-Image-2.5ClosedMicrosoft AI1,305±9
6—Nano Banana Pro (Gemini 3 Pro Image)ClosedGoogle1,298±9
7NewMAI-Image-2.5-ProClosedMicrosoft AI1,293±9
8▼ 1Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)ClosedGoogle1,288±9
9▼ 1Reve 2.0ClosedReve1,262±12
10▼ 1MAI-Image-2.5-FlashClosedMicrosoft AI1,228±10
11▼ 1Krea 2 LargeClosedKrea1,219±8
12▼ 1Krea 2 Medium TurboClosedKrea1,213±10
13—Krea 2 MediumClosedKrea1,212±8
14▼ 2MAI-Image-2ClosedMicrosoft AI1,211±8
15▼ 1GPT Image 1 (high)ClosedOpenAI1,202±10
16▼ 1Imagen 4 UltraClosedGoogle1,190±8
17▼ 1Nano Banana (Gemini 2.5 Flash Image)ClosedGoogle1,188±10
18▼ 1MAI-Image-2-EfficientClosedMicrosoft AI1,184±8
19▼ 1Imagen 3 (v002)ClosedGoogle1,127±8
20—Imagen 4 StandardClosedGoogle1,125±8
21▼ 2Lucid Origin UltraClosedLeonardo.Ai1,124±7
22▼ 1Reve Image (Halfmoon)ClosedReve1,115±9
23—Lucid Origin FastClosedLeonardo.Ai1,112±7
24▼ 2GPT Image 1 Mini (medium)ClosedOpenAI1,107±8
25▼ 1Ideogram 3.0ClosedIdeogram1,103±8
26▼ 1Imagen 4 FastClosedGoogle1,100±8
27▼ 1Midjourney v7 AlphaClosedMidjourney1,094±9
28▼ 1Ideogram v2ClosedIdeogram1,084±8
29▼ 1Midjourney v6ClosedMidjourney1,078±8
30▼ 1Ideogram v2 TurboClosedIdeogram1,077±8
31▼ 1MAI Image 1ClosedMicrosoft AI1,063±8
32▼ 1Midjourney v6.1ClosedMidjourney1,059±8
33▼ 1Ideogram v1ClosedIdeogram1,049±8
34▼ 1Phoenix 1.0 UltraClosedLeonardo.Ai1,043±8
35—Ideogram v2a TurboClosedIdeogram1,029±9
36▼ 2Phoenix 0.9 UltraClosedLeonardo.Ai1,029±8
37▼ 1Ideogram v2aClosedIdeogram1,028±9
38▼ 1Krea 1ClosedKrea1,014±9
39▼ 1Phoenix 1.0 FastClosedLeonardo.Ai1,007±8
40▼ 1Runway Gen-4 ImageClosedRunway994±9
41▼ 1DALLE 3ClosedOpenAI970±8
42▼ 1DALLE 3 HDClosedOpenAI968±8
43▼ 1Amazon Titan G1 v2 (Standard)ClosedAmazon924±8
44▼ 1Amazon Titan G1 (Standard)ClosedAmazon915±8
45▼ 1DALLE 2ClosedOpenAI746±10

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 “—”.