arena_system

Kimi K2.5 (Thinking) 2026-10-28

config_20ff5d44e0e312dbd1d86d55c67a7b1df9fd631de82eb16ca67720cfe00c9737

Published ranking

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

49%

capability score

Rank

85

Evidence families

1

Claim

Outside top set

Uncertainty was not reported

Configuration passport

Canonical name
Kimi K2.5 (Thinking)
Revision
2026-10-28
Interaction policy
crowd_pairwise
Passport class
arena-system-v1

Source evidence

Publication snapshotexplorer_57462ea7c921ad9a81e59706c6b8376f6525212f3cbdf7994f531d09cd5630ef

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