AgentTime v1.1 Update: GPT-6 Family Leads in AI Time Awareness

The AgentTime benchmark has been updated to v1.1, combining duration following, runtime forecasting, and retrospection into a single time-awareness score. GPT models, especially the GPT-6 family with GPT-6 Astra on top, clearly lead, while Claude models trail behind.

2026-11-03 ~ 2026-11-03 · 2 related posts

• AgentTime v1.1: GPT-6 Astra tops agent time-awareness benchmark at 51%, Claude trails — maksym_andr · 2026-11-03
• AgentTime Update: GPT Models Lead Time-Awareness, Best Forecast Miss Is 2.26× — maksym_andr · 2026-11-03