Skip to content
IFAI

Model rankings

569 models · 3 boards · 2 sources

‹
Week of September 29, 2025
November 10, 202510 changesNovember 3, 202523 changesOctober 27, 20253 changesOctober 20, 20252 changesOctober 13, 202518 changesOctober 6, 20257 changesSeptember 29, 202516 changesSeptember 22, 20258 changesSeptember 15, 20251 changeSeptember 8, 202513 changesSeptember 1, 20253 changesAugust 25, 202519 changes
›
Artificial AnalysisText-to-image arenaArenaText-to-image arena

Text-to-image arena · Anonymous head-to-head votes · Published October 3, 2025

Best images
hunyuan-image-3.0Tencent1,165Score
Best open model
hunyuan-image-3.0Tencent1,165Score
Best from China
hunyuan-image-3.0Tencent1,165Score
Most voted
qwen-image-prompt-extendAlibaba555,353Votes
Top three by Score
1hunyuan-image-3.0Tencent1,165
2gemini-2.5-flash-image-preview (nano-banana)Google1,151
3seedream-4-2kByteDance1,144
Top three open models
1hunyuan-image-3.0Tencent · #1 overall1,165
2qwen-image-prompt-extendAlibaba · #11 overall1,078
3qwen-imageAlibaba · #13 overall1,062
This week's changes
GPT-5 Codex (high)Intelligence · #2New
Claude 4.5 Sonnet (Reasoning)Intelligence · #7New
DeepSeek V3.1 Terminus (Reasoning)Intelligence · #13New
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)Intelligence · #34New
Qwen3 235B A22B 2507 InstructIntelligence · #39New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreVotes
RankChangeModelScore95% intervalVotes
1Newhunyuan-image-3.0OpenTencent1,165±103,333
2▼ 1gemini-2.5-flash-image-preview (nano-banana)ClosedGoogle1,151±3517,082
3Newseedream-4-2kClosedByteDance1,144±614,589
4▼ 2imagen-ultra-4.0-generate-001ClosedGoogle1,142±3437,734
5Newseedream-4-high-res-falClosedByteDance1,132±712,559
6▼ 3imagen-4.0-generate-001ClosedGoogle1,127±3438,948
7▼ 3gpt-image-1ClosedOpenAI1,126±3197,707
8▼ 3seedream-4-falClosedByteDance1,118±613,516
9▼ 2seedream-3ClosedByteDance1,081±530,686
10▼ 2flux-1-kontext-maxClosedBlack Forest Labs1,080±372,770
11▼ 5qwen-image-prompt-extendOpenAlibaba1,078±2555,353
12▼ 1imagen-3.0-generate-002ClosedGoogle1,063±3411,823
13▼ 4qwen-imageOpenAlibaba1,062±2106,821
14▼ 4flux-1-kontext-proClosedBlack Forest Labs1,062±3326,220
15▼ 3ideogram-v3-qualityClosedIdeogram1,049±529,252
16▼ 3lucid-originClosedLeonardo.Ai1,029±3270,663
17▼ 3recraft-v3ClosedRecraft1,019±4101,153
18▼ 1photonClosedLuma AI1,018±449,861
19▼ 4flux-1.1-proClosedBlack Forest Labs1,013±371,781
20▼ 4ideogram-v2ClosedIdeogram1,012±373,285
21▼ 3gemini-2.0-flash-preview-image-generationClosedGoogle989±3277,900
22▼ 3dall-e-3ClosedOpenAI978±4262,050
23▼ 2flux-1-dev-fp8OpenBlack Forest Labs966±449,919
24▼ 4flux-1-kontext-devOpenBlack Forest Labs963±3207,413
25▼ 3stable-diffusion-v35-largeOpenStability AI936±423,764
26▼ 3bagelOpenByteDance913±511,647

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 “—”.