Skip to main content
Glass bar chart topped with colored orbs
The models behind Aura’s chat modes, with independent scores from Artificial Analysis (intelligence, coding and agentic indexes) and Design Arena (head-to-head human votes on generated apps, sites and 3D). Data as of October 2026.

​
Where each model is used

​
Intelligence, coding and agentic indexes

Higher is better. ”—” means that index hasn’t been published for the model yet.
Glass podium with trophies and a radar chart

​
Design Arena rankings (human votes)

Rank among all models tested in each category.

​
Why Aura combines models

No single model wins everything. Opus leads on design and code, GPT-6 Astra on agentic work, Gemini 3.8 Flash on speed with native audio and video, Grok on live information. Orchestration asks four of them and compares, so you get each model’s strengths and catch their blind spots.

​
Price per million tokens

Aura upgrades models as better versions ship; the app always shows the version currently answering.