arena_system

Claude Opus 4.8 2026-10-28

config_4ba234aa493ae5cd6fea44ee1e421f71dd9703fcd0a57c609f05ea5fadfd41b5

Published ranking

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

63%

capability score

Rank

53

Evidence families

1

Claim

上位セット圏外

Uncertainty was not reported

Configuration passport

Canonical name
Claude Opus 4.8
Revision
2026-10-28
Interaction policy
crowd_pairwise
Passport class
arena-system-v1

出典エビデンス

Publication snapshotexplorer_57462ea7c921ad9a81e59706c6b8376f6525212f3cbdf7994f531d09cd5630ef

評価方法2026-10-31.1.cost-per-task-wave