OpenAI GPT-6 Astra Launch - Internal Data Science Tasks: leaderboard
OpenAI's internal data science task set, professional table of OpenAI's GPT-6 Astra launch post (2026-09-03). The tasks and grading are not published. Score in percent, higher is better. Scores are the maximum at any reasoning effort. Non-OpenAI models appear only where the post prints a value.
Metric: Score (%). Source: openai.com. Saturation forecast: Around 2028. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 40.9 | #6 |
| 2 | Claude Fable 5 | 34.7 | #20 |
| 3 | GPT-5.6 Sol | 30.5 | #22 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-6-astra-launch-internal-data-science-tasks · How It Works · Data refreshed daily, snapshot 2026-11-05.