10 actions in 9 pieces of software · ranked by words, meaning and measured trust · 608 ms
modelrecord11,642 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord141,280 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord
- moonshotai/kimi-k2.6
Moonshot AI's frontier open model, built for long-horizon coding, agent swarms, and autonomous software engineering. 1 trillion parameters, 262k context window, vision and tool use.
- moonshotai/kimi-k2.6
modelrecord
- moonshotai/kimi-k2.5
Moonshot AI's latest open model. It unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model
- moonshotai/kimi-k2.5
modelrecord
- tool-calling
Can call tools (function calling).
- structured-outputs
Can return JSON matching a schema.
- tool-calling
modelrecord
- moonshotai/kimi-k2-thinking
Kimi K2 Thinking is the latest, most capable version of an open-source thinking model.
- moonshotai/kimi-k2-thinking
libraryggml-org/llama.cpprecord5,488,885 downloads/month
- gguf
modelrecord
- text->text
Takes text; returns text.
- text->text
modelrecord226,231 downloads/month
- any-to-any
Task: any-to-any
- any-to-any
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.