LLM selection ·

“Which model should we use?” is a weighting problem.

Set how much each requirement matters for your job — reasoning, cost, latency, context, coding, tool use, multimodal — add hard constraints, and get a ranked shortlist of model classes with the reason for each, from an authored, dated matrix. Free. Nothing you set is uploaded.

10model classes
7weighted requirements
0bytes transmitted

What matters for your job?

The capability matrix

The authored scores (0–5) behind every result, dated . Qualitative tiers, not live specs — this is the judgement the ranking is built on, shown in full.

Pricing

The matcher, the ranked shortlist with reasons, and the full matrix are free and stay free. The Architect’s Edition adds what a matrix can’t: when each class is the wrong choice, the cost-control tactics that change the maths, and how to actually evaluate and decide.

Free
$0
  • Ranked shortlist of 10 model classes on your priorities
  • The reason and the watch-out for each
  • Hard filters — open-weights, self-hostable
  • The full authored, dated capability matrix
  • 100% client-side, nothing transmitted
Architect’s Edition
$29 one-time
  • When it’s the wrong choice — per class
  • Cost-control tactics that change the decision
  • The eval checklist — how to actually choose
  • Build vs buy vs self-host vs fine-tune, decided
Get the Architect’s Edition

Team licence for an engineering org? Email for a group rate.

Straight answers

Enter your licence code

Unlocks the Architect’s Edition on this device and survives reloads. No account, nothing transmitted.