Moonshot AI · Kimi K2

Kimi K2 Thinking Turbo

READER SUMMARY

The faster serving tier of Kimi K2 Thinking for high-throughput reasoning and agent tool use.

DOOM SCORE82.5out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 82.5

The underlying capabilities match Thinking, while faster serving and active API access increase practical deployment and slightly raise misuse and control difficulty.

Capability82
Autonomy88
Deployment99
Misuse potential74
Control difficulty77
MODEL-ATTRIBUTED EVIDENCE

News tied to Kimi K2 Thinking Turbo

The model score of 82.5 rates this model's risk profile. The overall Doom Index of 61.2 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.04

Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.

AUDIT TRAIL

Model score history

  1. R1
    Doom Score 82.5

    New exact public serving tier absent from the durable catalogue.

    11 Aug 2026