arena_system

Claude Opus 4.8 (High) 2026-10-19

config_a4daf4a5a4a0906e5aaf77fee4800c38f21f550c091f264550f120af0e156527

Published ranking

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

95%

capability score

Rank

20

Evidence families

1

Claim

Outside top set

Uncertainty was not reported

Configuration passport

Canonical name
Claude Opus 4.8 (High)
Revision
2026-10-19
Interaction policy
crowd_pairwise
Passport class
arena-system-v1

Source evidence

Publication snapshotexplorer_61482a3708a2f4f03780d4c4bf5f2b0dd1a93acc6cc765c940fbd55e11c3042a

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