arena_system

GPT-4.5 Preview (2025-02-27) 2026-10-19

config_0d096f0eac7f0dcd9e6805bbd9f252162214be1ff0183a64658c7eb8e3ea008b

Published ranking

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

80%

capability score

Rank

78

Evidence families

1

Claim

Outside top set

Uncertainty was not reported

Configuration passport

Canonical name
GPT-4.5 Preview (2025-02-27)
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