Data science
Data Science Tasks (OpenAI Internal)
OpenAI's own set of data-science jobs — taking a dataset and a question through cleaning, analysis and a defensible answer. Higher is better.
Rankings
Higher is betterData Science Tasks (OpenAI Internal) — frequently asked questions
- What is Data Science Tasks (OpenAI Internal)?
- OpenAI's own set of data-science jobs — taking a dataset and a question through cleaning, analysis and a defensible answer. Higher is better.
- Which AI model scores highest on Data Science Tasks (OpenAI Internal)?
- GPT-6 Astra by OpenAI holds the best Data Science Tasks (OpenAI Internal) result among tracked models, at 40.9% (released Sep 3 2026). Higher scores are better on this benchmark.
- What are the top 1 models on Data Science Tasks (OpenAI Internal)?
- 1. GPT-6 Astra (OpenAI) — 40.9%.
- How many models have a published Data Science Tasks (OpenAI Internal) score?
- 1 tracked model has a published Data Science 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.