agent_system

Claude Sonnet 4.6 (Max) automationbench:Claude Sonnet 4.6 (Max)

config_b98e2fee1d3cf0c74de948a3d0d45b5b80c9f51a16a7f5d660c823a1cb292226

Published ranking

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

10%

capability score

Rank

98

Evidence families

1

Claim

Outside top set

Uncertainty was not reported

Configuration passport

Canonical name
Claude Sonnet 4.6 (Max)
Revision
automationbench:Claude Sonnet 4.6 (Max)
Interaction policy
agentic
Passport class
agent-system-v1
Harness
zapier-automationbench
Scaffold
zapier-automationbench

Source evidence

Publication snapshotexplorer_53c3f60ade2779145e41fa6f4ddbace456bb0cafec9b02de8620c36f553be8cc

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