Skip to content
IFAI

Model rankings

1035 models · 5 boards · 2 sources

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

Text-to-image arena · Anonymous head-to-head votes · Updated March 3, 2026

Best images
GPT Image 1.5 (high)OpenAI1,268Score
Best open model
FLUX.2 [dev] TurboFal1,166Score
Best from China
Seedream 4.0ByteDance Seed1,188Score
Top three by Score
3Riverflow 2.0Sourceful1,252
Top three open models
1FLUX.2 [dev] TurboFal · #14 overall1,166
2Qwen Image Max 2512Alibaba · #16 overall1,151
3FLUX.2 [dev]Black Forest Labs · #17 overall1,151
This week's changes
GPT-5.3 Codex (xhigh)Intelligence · #2New
Qwen3.5 27B (Reasoning)Intelligence · #19New
Qwen3.5 122B A10B (Reasoning)Intelligence · #22New
qwen3.5-122b-a10bCoding · #22New
RankChangeModelScore95% interval
1—Seedream 4.0ClosedByteDance Seed1,188—
2—Seedream 4.5ClosedByteDance Seed1,173—
3▲ 1Wan 2.5 PreviewClosedAlibaba1,149—
4▼ 1Seedream 3.0ClosedByteDance Seed1,149—
5▲ 1Wan2.6 Text to ImageClosedAlibaba1,136—
6▼ 1Wan 2.6 ImageClosedAlibaba1,136—
7—Vivago 2.1ClosedHiDream1,126—
8—Kolors 2.1ClosedKlingAI1,125—
9—Vidu Q2ClosedVidu1,113—
10—Vivago 2.0ClosedHiDream1,104—
11—Dreamina 3.1ClosedByteDance1,081—
12—Qwen Image Plus 2601ClosedAlibaba1,060—
13—Image-01ClosedMiniMax1,046—
14—Z-Image BaseClosedAlibaba1,040—

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 “—”.