agent_system

Claude Opus 4.8 (XHigh) automationbench:Claude Opus 4.8 (XHigh)

config_57a659c9e83d821868dab27ab0c159c57b5c97fb718ac66d09d1c5fd5f6f6f87

Published ranking

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

31%

capability score

Rank

50

Evidence families

1

Claim

Outside top set

Uncertainty was not reported

Configuration passport

Canonical name
Claude Opus 4.8 (XHigh)
Revision
automationbench:Claude Opus 4.8 (XHigh)
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