AtelierEval - Prompt Constraint Coverage - Constrained Creation (Skilled Prompting): leaderboard
The 120 constrained creation tasks of AtelierEval (Luo et al., 2026): structured specifications of objects, attributes, layout, counts, exact text and hard constraints that the model must fit into one text-to-image prompt. Scored as the share of the constraint checklist of the task that the prompt specifies, checked by a GPT-5.4 judge, in percent (higher is better); the model receives a structured system prompt asking for chain-of-thought analysis and self-verification.
Metric: Prompt checklist coverage (%; share of each task's expert constraint checklist that the written prompt specifies, checked by a GPT-5.4 AtelierJudge; 120 constrained creation tasks: structured multi-constraint specifications; structured prompting with chain-of-thought and self-verification). Source: arxiv.org. Saturation forecast: Around 2031. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 37.4 | #111 |
| 2 | GPT-4.1 | 36.1 | #492 |
| 3 | GPT-5.2 | 35.6 | #172 |
| 4 | Qwen 3 VL 235B A22B | 35.3 | #477 |
| 5 | Claude Sonnet 4.5 | 33.2 | #244 |
| 6 | GPT-4.1 Nano | 32.4 | #1992 |
| 7 | Gemini 2.0 Flash | 27.1 | #702 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=ateliereval-prompt-constraint-coverage-constrained-creation-skilled-prompting · How It Works · Data refreshed daily, snapshot 2026-11-12.