Skip to content
IFAI

Model rankings

906 models · 5 boards · 2 sources

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

Text-to-image arena · Anonymous head-to-head votes · Published January 4, 2026

Best images
Best open model
hunyuan-image-3.0Tencent1,151Score
Best from China
hunyuan-image-3.0Tencent1,151Score
Top three open models
1hunyuan-image-3.0Tencent · #8 overall1,151
2flux-2-devBlack Forest Labs · #11 overall1,141
3qwen-image-2512Alibaba · #13 overall1,138
This week's changes
Speech 2.6 HDSpeech · #2New
Speech 2.6 TurboSpeech · #3New
minimax-m2.1-previewCoding · #5New
Multilingual v2Speech · #7New
GLM-4.7 (Reasoning)Intelligence · #8New
RankChangeModelScore95% intervalVotes
1—gpt-image-1.5-high-fidelityClosedOpenAI1,241±624,979
2—gemini-3-pro-image-preview-2k (nano-banana-pro)ClosedGoogle1,238±625,177
3—gemini-3-pro-image-preview (nano-banana-pro)ClosedGoogle1,233±559,957
4—flux-2-maxClosedBlack Forest Labs1,167±85,787
5▲ 1gemini-2.5-flash-image-preview (nano-banana)ClosedGoogle1,155±3696,915
6▼ 1flux-2-flexClosedBlack Forest Labs1,155±436,056
7—flux-2-proClosedBlack Forest Labs1,152±443,892
8—hunyuan-image-3.0OpenTencent1,151±4125,450
9▲ 2seedream-4-2kClosedByteDance1,145±614,514
10▲ 2imagen-ultra-4.0-generate-001ClosedGoogle1,144±4493,935
11▼ 2flux-2-devOpenBlack Forest Labs1,141±617,635
12▼ 2seedream-4.5ClosedByteDance1,139±614,578
13Newqwen-image-2512OpenAlibaba1,138±94,516
14▼ 1imagen-4.0-generate-001ClosedGoogle1,132±4494,178
15▲ 1seedream-4-falClosedByteDance1,118±613,453
16▼ 2wan2.5-t2i-previewClosedAlibaba1,117±563,701
17▼ 2seedream-4-high-res-falClosedByteDance1,116±486,126
18▼ 1gpt-image-1ClosedOpenAI1,115±3265,717
19▼ 1gpt-image-1-miniClosedOpenAI1,104±467,737
20▼ 1mai-image-1ClosedMicrosoft AI1,091±456,516
21▼ 1seedream-3ClosedByteDance1,084±541,723
22▼ 1flux-1-kontext-maxClosedBlack Forest Labs1,078±372,524
23▼ 1qwen-image-prompt-extendOpenAlibaba1,067±3676,354
24▼ 1flux-1-kontext-proClosedBlack Forest Labs1,065±3392,964
25▼ 1imagen-3.0-generate-002ClosedGoogle1,062±3424,114
26▼ 1qwen-imageOpenAlibaba1,060±2106,419
27▼ 1ideogram-v3-qualityClosedIdeogram1,054±4103,658
28▼ 1photonClosedLuma AI1,037±4116,728
29▼ 1recraft-v3ClosedRecraft1,026±4166,992
30▼ 1lucid-originClosedLeonardo.Ai1,022±3336,945
31▼ 1flux-1.1-proClosedBlack Forest Labs1,019±371,781
32▼ 1ideogram-v2ClosedIdeogram1,018±373,285
33▼ 1gemini-2.0-flash-preview-image-generationClosedGoogle986±3305,273
34▼ 1dall-e-3ClosedOpenAI978±4267,466
35▼ 1flux-1-dev-fp8OpenBlack Forest Labs973±449,919
36▼ 1flux-1-kontext-devOpenBlack Forest Labs959±3257,871
37▼ 1stable-diffusion-v35-largeOpenStability AI942±423,764
38▼ 1bagelOpenByteDance911±611,600

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 “—”.