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%.
More from coding & agent
- Higgsfield Launches MCP 2.0 for Claude, Bringing Its Creative Studio Into Chat — piotrbinkowski · 2026-11-19
- CoRL workshop: running Karpathy's autoresearch on real robots — the sandbox, not the model, is the bottleneck — Kyrannio · 2026-11-19
- OpenAI data: 90th-percentile researcher now spends $23,000 on agentic AI tools — kliu128 · 2026-11-19
- Web search grounding cut a calling agent's booking accuracy by 5+ points across 2,415 tests — Evening_Hawk_7470 · 2026-11-19
- Gemini 4 Neon lands Day 0 in LangChain's Managed Deep Agents for long-running agent work — hwchase17 · 2026-11-19
- badlogic: agents 'reward-hack' past your lint rules and tests—without insight under the hood, your verifications may be worthless — teropa · 2026-11-19