Skip to content
IFAI

Model rankings

1388 models · 5 boards · 2 sources

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

Text-to-image arena · Anonymous head-to-head votes · Updated July 29, 2026

Best images
GPT Image 2 (high)OpenAI1,340Score
Best open model
Best from China
HiDream-O1-Image-1.5HiDream1,246Score
Top three by Score
1GPT Image 2 (high)OpenAI1,340
2Reve 2.1Reve1,299
3MAI-Image-2.5Microsoft AI1,270
Top three open models
1Cosmos3-Super-Text2Image (agentic)NVIDIA · #12 overall1,218
2HiDream-O1-Image-Dev-2604HiDream · #21 overall1,190
3Cosmos3-Super-Text2Image-4StepNVIDIA · #25 overall1,182
This week's changes
claude-opus-5-maxCoding · #1New
Reve 2.1Image · #2New
MiniMax H3Video · #2New
qwen3.8-maxCoding · #4New
RankChangeModelScore95% interval
1—GPT Image 2 (high)ClosedOpenAI1,340±7
2NewReve 2.1ClosedReve1,299±11
3▼ 1MAI-Image-2.5ClosedMicrosoft AI1,270±9
4—GPT Image 1.5 (high)ClosedOpenAI1,263±7
4▲ 1Nano Banana 2 (Gemini 3.1 Flash Image Preview)ClosedGoogle1,263±7
6▼ 3Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)ClosedGoogle1,263±9
7▼ 1Reve 2.0ClosedReve1,241±10
8▼ 1Nano Banana Pro (Gemini 3 Pro Image)ClosedGoogle1,226±7
9▼ 1MAI-Image-2.5-FlashClosedMicrosoft AI1,208±9
10—Krea 2 LargeClosedKrea1,190±7
11▼ 2Krea 2 MediumClosedKrea1,190±7
12▼ 1MAI-Image-2ClosedMicrosoft AI1,189±7
13NewKrea 2 Medium TurboClosedKrea1,186±10
14▼ 1Imagen 4 UltraClosedGoogle1,172±8
15—MAI-Image-2-EfficientClosedMicrosoft AI1,159±7
16—Nano Banana (Gemini 2.5 Flash Image)ClosedGoogle1,153±7
17—GPT Image 1 (high)ClosedOpenAI1,138±8
18—Lucid Origin UltraClosedLeonardo.Ai1,120±8
19—Lucid Origin FastClosedLeonardo.Ai1,109±8
20—Imagen 3 (v002)ClosedGoogle1,107±8
21—Imagen 4 StandardClosedGoogle1,101±8
22—Reve Image (Halfmoon)ClosedReve1,099±8
23—GPT Image 1 Mini (medium)ClosedOpenAI1,093±8
24▲ 1Ideogram 3.0ClosedIdeogram1,078±8
25▲ 1Imagen 4 FastClosedGoogle1,075±8
26▲ 1Ideogram v2ClosedIdeogram1,073±7
27▲ 1Midjourney v7 AlphaClosedMidjourney1,069±8
28▲ 1Midjourney v6ClosedMidjourney1,068±7
29▲ 1Ideogram v2 TurboClosedIdeogram1,058±7
30▲ 1Midjourney v6.1ClosedMidjourney1,053±7
31▲ 1MAI Image 1ClosedMicrosoft AI1,042±8
32▲ 1Ideogram v1ClosedIdeogram1,034±8
33▲ 1Phoenix 1.0 UltraClosedLeonardo.Ai1,032±8
34▲ 2Ideogram v2aClosedIdeogram1,015±8
35▲ 2Ideogram v2a TurboClosedIdeogram1,015±8
36▲ 2Phoenix 0.9 UltraClosedLeonardo.Ai1,011±8
37▲ 3Krea 1ClosedKrea1,005±8
38▲ 4Phoenix 1.0 FastClosedLeonardo.Ai995±8
39▲ 4Runway Gen-4 ImageClosedRunway977±8
40▲ 4DALLE 3 HDClosedOpenAI959±8
41▲ 5DALLE 3ClosedOpenAI950±8
42▲ 6Amazon Titan G1 v2 (Standard)ClosedAmazon912±8
43▲ 6Amazon Titan G1 (Standard)ClosedAmazon900±8
44▲ 6DALLE 2ClosedOpenAI744±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 “—”.