agent_system

Claude Opus 4.8 (Max) automationbench:Claude Opus 4.8 (Max)

config_6fc288bc8171bcb11a4d115a1236362d6f2c1cace393b9455376b1a7446a6bd0

Published ranking

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

31%

capability score

Rank

52

Evidence families

1

Claim

上位セット圏外

Uncertainty was not reported

Configuration passport

Canonical name
Claude Opus 4.8 (Max)
Revision
automationbench:Claude Opus 4.8 (Max)
Interaction policy
agentic
Passport class
agent-system-v1
Harness
zapier-automationbench
Scaffold
zapier-automationbench

出典エビデンス

Publication snapshotexplorer_53c3f60ade2779145e41fa6f4ddbace456bb0cafec9b02de8620c36f553be8cc

評価方法2026-10-31.1.cost-per-task-wave