10 actions in 6 pieces of software · ranked by words, meaning and measured trust · 657 ms
modelrecord85,126 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord13,978 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord
- zsxkib/kimi-vl-a3b-thinking
Kimi-VL-A3B-Thinking is a multi-modal LLM that can understand text and images, and generate text with thinking processes
- zsxkib/kimi-vl-a3b-thinking
modelrecord222,419 downloads/month
- any-to-any
Task: any-to-any
- any-to-any
modelrecord
- structured-outputs
Can return JSON matching a schema.
- text->text
Takes text; returns text.
- tool-calling
Can call tools (function calling).
- structured-outputs
modelrecord
- h100-80gb-hbm3
Task: H100 80GB HBM3
- b200
Task: B200
- h200
Task: H200
- h100-80gb-hbm3
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.