# Data Science Tasks (OpenAI Internal) — AI model rankings

OpenAI's own set of data-science jobs — taking a dataset and a question through cleaning, analysis and a defensible answer. Higher is better.

1 tracked model have a published Data Science Tasks (OpenAI Internal) score. Higher is better. Scores are as published at each model's release.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | GPT-6 Astra | OpenAI | 40.9% | Lab | Sep 3 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/openai-data-science-tasks
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Benchmark scores are the figures published by the releasing lab at launch.