Add model-index eval YAML, arch spec, thinking docs, limitations, citation, ModelScope; remove column meanings note

SEO/GEO: rewrite intro with keyword-rich quotable authoritative content

Link v3 model family and previous releases in Related repos

Remove base column note from 8-metric table

Fix table formatting: remove blank lines between rows throughout README

Fix 8-metric table: add v2 numbers and correct base (thinking-ON) values

Fix YAML metadata frontmatter formatting in README card

Align benchmark metrics exactly with main MiniCPM5-1B-Agentic-Tooluse repository and remove non-baseline sections

Update README with full 8-metric benchmark and matched baseline table

Update baseline metric results to match main repository

Add footnote explaining base-model number discrepancy vs an older, differently-conditioned repo

Add fresh, full 8-metric benchmark table (matches v2-era report format) and v3-vs-v4 validation note

Expand README: SEO-optimized, fix v2 baseline label

Add README with real measured v3 results

v3 LoRA adapter

initial commit