model roundup

Gemini 3.8

3 items · started 2026-09-15 · ongoing (last activity 2026-09-18)

  1. 5 models, 55 tasks, 675 attempts. Which models can actually do parametric CAD, graded on build success, measured geometry, and a checklist judge.

  2. Gemini 3.8 Live Extended Thinking is our high-reasoning audio-to-audio model recommended when higher background reasoning is required for complex, multi-step problem solving during real-time voice interactions. It processes background reas…

← all threads