Decision guide · free roster vs paid frontier

Benchmarks

Start with the best free model for a common task, then inspect category detail against one paid reference model. Scores use the public Artificial Analysis dataset.

Data source: Live Artificial Analysis dataLast generated: 2026-11-09 18:00

Reading the scores: ‡ and “paid proxy” mean the free roster model has no free-variant AA record, so the paid variant is shown as a clearly labelled proxy. It is not a free-tier measurement.

Coverage: Agentic coding / terminal, Scientific reasoning require an Artificial Analysis Pro key and are not shown.

Everyday model

nvidia/nemotron-3-ultra-550b-a55b:free11.80‡paid proxy

Highest general intelligence score in the current free roster.

Engineering

nvidia/nemotron-3-ultra-550b-a55b:free22.80‡paid proxy

Highest applied engineering score in the current free roster.

Overall intelligence

AA Intelligence Index — general knowledge, reasoning, agents, and scientific performance. 14 roster models without this metric are omitted.

Overall intelligence free models and paid reference
ModelScore
nvidia/nemotron-3-ultra-550b-a55b:freeFree 11.80‡★paid proxy
nvidia/nemotron-3.5-lightning:freeFree 5.50‡paid proxy
nemotron-3.5-lightning-freeFree 5.50‡paid proxy
Paid reference 60.00

Applied engineering

AA Engineering Index — applied engineering and systems reasoning. 14 roster models without this metric are omitted.

Applied engineering free models and paid reference
ModelScore
nvidia/nemotron-3-ultra-550b-a55b:freeFree 22.80‡★paid proxy
nvidia/nemotron-3.5-lightning:freeFree 15.50‡paid proxy
nemotron-3.5-lightning-freeFree 15.50‡paid proxy
Paid reference 65.30