AtelierEval - Image Constraint Satisfaction (Novice Prompting): leaderboard

Metric: Image checklist satisfaction (%; share of each task's expert constraint checklist realized in the generated image, best of four images per backend, mean over four text-to-image backends (Gemini 3 Pro Image, GPT-Image-1, Flux.1 Pro, SDXL) and the three task categories, GPT-5.4 AtelierJudge; direct natural-language prompting). Source: arxiv.org. Saturation forecast: Around 2029. 8 models tracked.

Top models

#ModelScore
1GPT-5.265.7
2Gemini 3 Pro (Preview)64.7
3Claude Sonnet 4.564.1
4GPT-4.163
5Qwen 3 VL 235B A22B61.3
6Gemini 2.0 Flash60.9
7GPT-4.1 Nano60.8
8Qwen 3 VL 8B57.8

Interactive version: theaggregate.ai/benchmark?slug=ateliereval-image-constraint-satisfaction-novice-prompting · How It Works · Data refreshed daily, snapshot 2026-09-26.