Three computer-use benchmarks fall to GPT-6 Astra
OpenAI says its new flagship holds state-of-the-art results on Agents’ Last Exam, AutomationBench and ScreenSpot Pro, benchmarks that measure computer workflow tasks across professions. The claim went out on X without any accompanying numbers.
A second post stretches the list to FrontierMath Tier 4, ARC-AGI 3 and TerminalBench-4.0, and calls Astra a major advance for scientific discovery with state-of-the-art performance on Terminal-Bench Science 0.1 and HealthBench Pro. On ARC-AGI 3, the run ARC Prize published on September 3 put Astra at 99.9% under the Provider Adapter harness.
Up next
A Schumer lands in OpenAI’s Washington operation
Chuck Schumer’s daughter is heading to OpenAI’s policy team, per Axios citing a company spokesperson. Jessica Schumer, Amazon’s former top public-policy official in New York, will run its government outreach in the Northeast.
Related stories
- OpenAI trains GPT-6 Astra on real Ironclad contract work
- GPT-6 Astra ships and Brockman declares the AGI era
- A harness swap took Astra from 62.7% to 99.9%
- Same model, better scaffolding: 13.3% to 38.3% on ARC-AGI-3
- GPT-6 Astra designed a Codex device in under a week
- Opus 5.5 edges GPT-6 Astra, 58 to 57, on Artificial Analysis
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.