Today for AI
HOT RADAR
agentHEAT 15.5°

AI CURATED HOT STORY · 11/13/2026

Deepnote Launches Agent Initiative Benchmark for Proactive Agents

1 reports archived1 independent sourcesupdated 11/13/2026, 23:24:29
Synthesis & Latest Updates
1 Sources Cross-Validated

Deepnote released the Agent Initiative Benchmark, which drops proactive agents into a simulated company Slack and scores whether they know when to intervene, what to say, and when to stay silent. GPT-6 Astra led at 8.97 out of 10, with GPT-6.1 Sol close behind at 8.65 at just $0.11 per task, versus $1.87 per task for third-placed Claude Fable 5.2. The open-source dataset and benchmark code give builders a reproducible basis for choosing models for proactive agent use cases.

LATEST/Deepnote released the Agent Initiative Benchmark, which drops proactive agents into a simulated company Slack and scores whether they know when to intervene, what to say, and when to stay silent. GPT-6 Astra led at 8.97 out of 10, with GPT-6.1 Sol close behind at 8.65 at just $0.11 per task, versus $1.87 per task for third-placed Claude Fable 5.2. The open-source dataset and benchmark code give builders a reproducible basis for choosing models for proactive agent use cases.

Hourly heat curve

2 fully observed hours
Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first
  1. Rohan Paul (@rohanpaul_ai)T2·72 pts

    Deepnote Launches Agent Initiative Benchmark for Proactive Agents

    • Agents are placed in a synthetic company Slack with six years of detailed history, testing proactive intervention judgment, service selection, and people tagging
    • GPT-6 Astra led at 8.97, while GPT-6.1 Sol scored 8.65 at only $0.11 per task, far cheaper than third-placed Claude Fable 5.2 at $1.87
    • Two LLM evaluators score runs against reference answers, and both the dataset and benchmark code are open-sourced