Kimi K2 Instruct
Open-weight Kimi K2 instruction model optimized for tool use, coding and agentic tasks.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 80.0
Instruction tuning and tool-use training materially raise autonomy and misuse readiness, while open weights and broad access make monitoring and containment difficult.
News tied to Kimi K2 Instruct
The model score of 80.0 rates this model's risk profile. The overall Doom Index of 66.8 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current 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 use a bounded temporal offset around their technical profile, but never feed back into the overall index.
Moonshot AI releases open-weight Kimi K2 base and instruction models
Moonshot AI published Kimi K2, a trillion-parameter mixture-of-experts family with 32 billion active parameters, open weights and an instruction model designed for tool use and agentic tasks.
- Full item contribution
- +0.18
- Kimi K2 Instruct equal share
- +0.09
Model score history
-
R3
Doom Score 80.0
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R2
Doom Score 79.9
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R1
Doom Score 79.7
New exact public instruction model profile with authoritative repository creation timestamp.
12 Aug 2026