Design work
Design Tasks (OpenAI Internal)
OpenAI's own set of professional design briefs, scored on whether the finished work is what a designer would have handed over. Higher is better.
Rankings
Higher is betterDesign Tasks (OpenAI Internal) — frequently asked questions
- What is Design Tasks (OpenAI Internal)?
- OpenAI's own set of professional design briefs, scored on whether the finished work is what a designer would have handed over. Higher is better.
- Which AI model scores highest on Design Tasks (OpenAI Internal)?
- GPT-6 Astra by OpenAI holds the best Design Tasks (OpenAI Internal) result among tracked models, at 50% (released Sep 3 2026). Higher scores are better on this benchmark.
- What are the top 1 models on Design Tasks (OpenAI Internal)?
- 1. GPT-6 Astra (OpenAI) — 50%.
- How many models have a published Design Tasks (OpenAI Internal) score?
- 1 tracked model has a published Design Tasks (OpenAI Internal) score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.