arena_system

gpt-5.4-high (codex-harness) 2026-10-01

config_0d5168754e38811fa422763eb61691f5aef8e888cab8a599b096ad0ae0485564

Published ranking

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

53%

capability score

Rank

63

Evidence families

1

Claim

Outside top set

Uncertainty was not reported

Configuration passport

Canonical name
gpt-5.4-high (codex-harness)
Revision
2026-10-01
Interaction policy
crowd_pairwise
Passport class
arena-system-v1

Source evidence

Publication snapshotexplorer_d0403766563286248b76ce1c9785505a1d581fe1e48708622c42012bda934507

Methodology2026-10-04.1.macroscopebench-code-review-wave