Arena-T2I Hard - Text Rendering: leaderboard

Metric: Faithfulness on the Arena-T2I Hard prompts whose primary category is text rendering: dependency-aware faithfulness yes-ratio (%; share of the about 30 decomposed yes/no constraint questions per prompt that a gemini-3-flash judge answers yes for the generated image, a question counted only when its parent questions pass); higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 11 models tracked.

Top models

#ModelScore
1gemini-3-pro-image-preview-2k90.6
2Grok Imagine Image 2026030688.1
3recraft-v481.7
4wan2.6-t2i-v280
5gemini-2.5-flash-image75
6gpt-image-1.5-high-fidelity74.4
7gpt-image-172.6
8imagen-4.0-ultra-generate-00165.9
9imagen-4.0-generate-00160.2
10ideogram-v3-quality57

Interactive version: theaggregate.ai/benchmark?slug=arena-t2i-hard-text-rendering · How It Works · Data refreshed daily, snapshot 2026-09-29.