Card: crisper card, computer use first

Card: link Screen click and the Computer use docs

Code revision v1.4: opt-in vLLM server (text only)

Code revision v1.3: opt-in screenshot input (self-hosted)

Card: official JevBench column says no official score published

Shorter card; link the API docs

Card: links to the source code and docs

v1.2: TypeSafe API wire compatibility in serve.py (server-side SDKs, GET /v1/models, optional API key, error detail, request ids; a full batching queue answers 529); score answers carry confidence; weights unchanged

Card: local Decision Index 0.2 run (descriptive; known training exposure not penalized) and its evidence file

Card: the JSON-object note applies to the TypeSafe cases only

v1.1: opt-in cross-request batching in serve.py (--batch-window-ms, off by default); weights unchanged

Card: architecture, post-training and readout diagrams

Card and licence corrections: audit scope, reproduction wording, MiMo lineage

blink v1.0