Skip to content
IFAI

Model rankings

1035 models · 5 boards · 2 sources

‹
Week of March 2, 2026
April 13, 202637 changesApril 6, 202641 changesMarch 30, 2026230 changesMarch 23, 202626 changesMarch 16, 202622 changesMarch 9, 202665 changesMarch 2, 202663 changesFebruary 23, 202613 changesFebruary 16, 202616 changesFebruary 9, 202641 changesFebruary 2, 20266 changesJanuary 26, 2026177 changes
›
Artificial AnalysisText-to-image arenaArenaText-to-image arena

Text-to-image arena · Anonymous head-to-head votes · Published March 6, 2026

Best images
gemini-3.1-flash-image-preview (nano-banana-2) [web-search]Google1,268Score
Best open model
hunyuan-image-3.0Tencent1,152Score
Best from China
hunyuan-image-3.0Tencent1,152Score
Most voted
gemini-2.5-flash-image-preview (nano-banana)Google680,525Votes
Top three by Score
1gemini-3.1-flash-image-preview (nano-banana-2) [web-search]Google1,268
2gpt-image-1.5-high-fidelityOpenAI1,248
3gemini-3-pro-image-preview-2k (nano-banana-pro)Google1,236
Top three open models
1hunyuan-image-3.0Tencent · #12 overall1,152
2flux-2-devBlack Forest Labs · #13 overall1,149
3qwen-image-2512Alibaba · #17 overall1,139
This week's changes
GPT-5.3 Codex (xhigh)Intelligence · #2New
gpt-5.3-codex (codex-harness)Coding · #13New
Qwen3.5 27B (Reasoning)Intelligence · #19New
Qwen3.5 122B A10B (Reasoning)Intelligence · #22New
qwen3.5-122b-a10bCoding · #22New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreVotes
RankChangeModelScore95% intervalVotes
1—gemini-3.1-flash-image-preview (nano-banana-2) [web-search]ClosedGoogle1,268±714,729
2—gpt-image-1.5-high-fidelityClosedOpenAI1,248±555,118
3—gemini-3-pro-image-preview-2k (nano-banana-pro)ClosedGoogle1,236±552,541
4—gemini-3-pro-image-preview (nano-banana-pro)ClosedGoogle1,233±583,574
5—reve-v1.5ClosedReve1,177±68,013
6Newgrok-imagine-imageClosedxAI1,175±439,932
7Newgrok-imagine-image-proClosedxAI1,162±439,822
8▼ 2gemini-2.5-flash-image-preview (nano-banana)ClosedGoogle1,156±3680,525
9▼ 2imagen-ultra-4.0-generate-001ClosedGoogle1,148±4390,079
10▼ 2imagen-4.0-generate-001ClosedGoogle1,133±3455,020
11▼ 2gpt-image-1ClosedOpenAI1,115±3265,597
12▼ 2gpt-image-1-miniClosedOpenAI1,104±498,590
13▼ 2mai-image-1ClosedMicrosoft AI1,095±486,735
14▼ 2imagen-3.0-generate-002ClosedGoogle1,059±3361,554
15▼ 2ideogram-v3-qualityClosedIdeogram1,050±4115,713
16▼ 2photonClosedLuma AI1,037±4127,889
17▼ 2lucid-originClosedLeonardo.Ai1,015±3287,488
18▼ 2ideogram-v2ClosedIdeogram1,014±372,113
19▼ 2gemini-2.0-flash-preview-image-generationClosedGoogle976±3258,626
20▼ 2dall-e-3ClosedOpenAI969±4240,451

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 “—”.