10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 775 ms
modelrecord
- tool-calling
Can call tools (function calling).
- structured-outputs
Can return JSON matching a schema.
- text->text
Takes text; returns text.
- tool-calling
modelrecord
- deepseek-ai/deepseek-v3.1
Latest hybrid thinking model from Deepseek
- deepseek-ai/deepseek-v3.1
modelrecord
- text+image->text
Takes text, image; returns text.
- text+image->text
modelrecord
- deepseek-ai/janus-pro-7b
Janus-Pro is a novel autoregressive framework for multimodal understanding
- deepseek-ai/janus-pro-7b
modelrecord
- deepseek-ai/janus-pro-1b
Janus-Pro is a novel autoregressive framework for multimodal understanding
- deepseek-ai/janus-pro-1b
modelrecord
- deepseek-ai/deepseek-v3
DeepSeek-V3-0324 is the leading non-reasoning model, a milestone for open source
- deepseek-ai/deepseek-v3
- ask_deepseek
Ask Deepseek — Ask Deepseek anything you want!
- ask_deepseek
- 8DeepSeek-V4-Pro-0813 Demodemo or tutorialno passport yet
MCP serverrecord
- deepseek_v4_pro_0813_demo__check_login_status
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.