Skip to content

Back to the catalog

Harrison Kinsley (@Sentdex) on X
x.comthread

Harrison Kinsley (@Sentdex) on X

Sentdex reacts to Artificial Analysis ranking NVIDIA's Nemotron 3.5 Super VL (120B total, 12B active MoE) as the top US open-weights model, scoring 26 on the Intelligence Index. That edges out Thinking Machines' Inkling Small (26), NVIDIA's Nemotron 3 Ultra (23) and Meta's Muse Glimmer (17). Sentdex's informal tests at vanilla settings show over 550 tok/sec, and they suspect it would rank higher on agentic coding. They see it as a candidate for a fast local coding agent model.

TL;DR Nemotron 3.5 Super VL (120B A12B) tops US open-weights models at 26 on the AA Intelligence Index; Sentdex measures 550+ tok/sec and sees promise as a local coding agent.
Open original ↗

Organisations named here

  • NVIDIA
  • Thinking Machines
  • Meta
  • Artificial Analysis
  • Thinking Machines Lab
  • Nemotron
  • Sentdex

Technologies named here

  • Nemotron 3.5 Super VL
  • Inkling Small
  • Nemotron 3 Ultra
  • Muse Glimmer
  • Vision language model
  • Artificial Analysis Intelligence Index
  • Muse
  • Mixture of Experts

Related in models