AtelierEval - Prompt Constraint Coverage - Constrained Creation (Skilled Prompting): leaderboard
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 2032. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 37.4 |
| 2 | GPT-4.1 | 36.1 |
| 3 | GPT-5.2 | 35.6 |
| 4 | Qwen 3 VL 235B A22B | 35.3 |
| 5 | Claude Sonnet 4.5 | 33.2 |
| 6 | GPT-4.1 Nano | 32.4 |
| 7 | Gemini 2.0 Flash | 27.1 |
| 8 | Qwen 3 VL 8B | 26.9 |
Interactive version: theaggregate.ai/benchmark?slug=ateliereval-prompt-constraint-coverage-constrained-creation-skilled-prompting · How It Works · Data refreshed daily, snapshot 2026-09-26.