Kimi K2 Thinking! The Open-Source Thinking Agent Model is here.
Some are saying it is good at writing.
It is also topping the charts for tool use.
I haven't tested it out yet..
Let us know if you have a chance to test and what tasks it is good at for you
....
SOTA on HLE (44.9%) and BrowseComp (60.2%)
Executes up to 200 – 300 sequential tool calls without human interference Excels in reasoning, agentic search, and coding 256K context window
Built as a thinking agent, K2 Thinking marks our latest efforts in test-time scaling — scaling both thinking tokens and tool-calling turns.
K2 Thinking is now live on http://kimi.com in chat mode, with full agentic mode coming soon. It is also accessible via API.