OpenAI internal data shows smooth gains in autonomous research task length

kliu128 · x · 2026-11-19

OpenAI's internal report shows smooth improvement in the length of research tasks models complete autonomously, measured with an upgraded pipeline. Zero-intervention task success rates, bucketed by estimated human task duration (<15m to 8h+), rose steadily from March through October: e.g., 1–2 hour tasks went from 35% to 55%, and 8h+ tasks from 10% to 29%.

Related event: OpenAI Reveals Internal Research-Acceleration Data: 7x Code Changes, Safety Effort Up 77.2%(9 posts)→

Original post →

More from coding & agent

coding & agent channel →