arena_system

Kimi K2.5 (Thinking) 2026-10-19

config_456ccd430ee7d07a786f6e9074f251c36e47546caf4b11e989316a9ef942d4a7

Published ranking

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

87%

capability score

Rank

51

Evidence families

1

Claim

Outside top set

Uncertainty was not reported

Configuration passport

Canonical name
Kimi K2.5 (Thinking)
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