Skip to content
IFAI

Model rankings

1190 models · 5 boards · 2 sources

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

Text-to-image arena · Anonymous head-to-head votes · Published April 23, 2026

Best images
gpt-image-2 (medium)OpenAI1,507Score
Best open model
hunyuan-image-3.0Tencent1,151Score
Best from China
Top three open models
1hunyuan-image-3.0Tencent · #15 overall1,151
2flux-2-devBlack Forest Labs · #16 overall1,149
3qwen-image-2512Alibaba · #20 overall1,133
This week's changes
Grok 4.3Intelligence · #8New
mimo-v2.5-proCoding · #9New
gpt-5.5 (codex-harness)Coding · #15New
RankChangeModelScore95% intervalVotes
1—gpt-image-2 (medium)ClosedOpenAI1,507±915,391
2—gemini-3.1-flash-image-preview (nano-banana-2) [web-search]ClosedGoogle1,271±555,988
3—gemini-3-pro-image-preview-2k (nano-banana-pro)ClosedGoogle1,244±494,356
4—gpt-image-1.5-high-fidelityClosedOpenAI1,242±499,255
5—gemini-3-pro-image-preview (nano-banana-pro)ClosedGoogle1,232±582,657
6—mai-image-2ClosedMicrosoft AI1,183±533,666
7—reve-v1.5ClosedReve1,177±67,807
8—grok-imagine-imageClosedxAI1,170±4133,627
9—qwen-image-2.0-pro-2026-04-22ClosedAlibaba1,167±85,122
10—flux-2-maxClosedBlack Forest Labs1,165±497,415
11—grok-imagine-image-proClosedxAI1,158±481,749
12—flux-2-proClosedBlack Forest Labs1,157±3132,390
13—flux-2-flexClosedBlack Forest Labs1,156±4128,862
14—gemini-2.5-flash-image-preview (nano-banana)ClosedGoogle1,152±3757,256
15—hunyuan-image-3.0OpenTencent1,151±3172,985
16—flux-2-devOpenBlack Forest Labs1,149±554,558
17—imagen-ultra-4.0-generate-001ClosedGoogle1,148±4389,661
18—seedream-4.5ClosedByteDance1,142±3165,241
19—seedream-4-2kClosedByteDance1,140±712,627
20—qwen-image-2512OpenAlibaba · 1 more variant1,133±461,000
21—wan2.6-t2iClosedAlibaba1,132±4118,991
22—imagen-4.0-generate-001ClosedGoogle1,130±3501,132
23—wan2.5-t2i-previewClosedAlibaba1,117±3176,094
24—seedream-5.0-liteClosedByteDance1,117±454,186
25—qwen-image-2.0-2026-03-03ClosedAlibaba1,117±538,447
26—seedream-4-falClosedByteDance1,116±611,863
27—gpt-image-1ClosedOpenAI1,115±3265,541
28—seedream-4-high-res-falClosedByteDance1,112±3154,144
29—recraft-v4ClosedRecraft1,109±553,540
30—gpt-image-1-miniClosedOpenAI1,105±3142,957
31—wan2.7-image-proClosedAlibaba1,104±528,141
32—wan2.7-imageClosedAlibaba1,099±528,446
33—mai-image-1ClosedMicrosoft AI1,093±494,494
34—z-image-turboOpenAlibaba1,083±615,874
35—seedream-3ClosedByteDance1,082±536,925
36—flux-1-kontext-maxClosedBlack Forest Labs1,074±365,951
37—flux-2-klein-9bOpenBlack Forest Labs1,069±3111,598
38—qwen-image-prompt-extendOpenAlibaba1,060±3674,166
39—flux-1-kontext-proClosedBlack Forest Labs1,059±3332,198
40—imagen-3.0-generate-002ClosedGoogle1,058±3361,420
41—ideogram-v3-qualityClosedIdeogram1,049±4115,295
42—p-imageClosed1,036±480,989
43—photonClosedLuma AI1,035±4127,564
44—flux-2-klein-4bOpenBlack Forest Labs1,027±3113,383
45—runway-gen4ClosedRunway1,026±533,299
46—recraft-v3ClosedRecraft1,021±4192,009
47—flux-1.1-proClosedBlack Forest Labs1,016±370,460
48—ideogram-v2ClosedIdeogram1,013±372,090
49—lucid-originClosedLeonardo.Ai1,013±3286,562
50—glm-imageOpenZ.ai1,011±94,612

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 “—”.