agent_system

GPT-6 Astra (Max) deepsecbench-aa:2f339a97-9a0d-499a-9cb5-e0db665bfa25

config_4d9b933720cbb942b3ce8e62a6339d2fc1a934cc2886c88c83ce213d2932b597

Published ranking

This score and claim apply only inside the bound ranking group.

76%

capability score

Rank

2

Evidence families

1

Claim

Outside top set

Uncertainty was not reported

Configuration passport

Canonical name
GPT-6 Astra (Max)
Revision
deepsecbench-aa:2f339a97-9a0d-499a-9cb5-e0db665bfa25
Interaction policy
agentic
Passport class
agent-system-v1
Harness
artificialanalysis-stirrup
Scaffold
artificialanalysis-stirrup

Source evidence

Publication snapshotexplorer_5ed2585e80e4a96d9b23343667d20b4592947ffe8e62e67abf62b1ff72a8ee37

Methodology2026-10-31.1.cost-per-task-wave