2 new models powering Lovable today: Claude Opus 5.5 and GPT-6 Sol.
You don't need to think about which to use. Lovable combines the best models to get the result you want.
Pretty much every week, a new AI model drops.
(Speaking of: Lovable now builds with Fable 5.1)
We test each new model, tune it, and decide how it’s routed to ensure your builds have the best outcome.
Our job is to keep up, your job is to keep building.
Read more about our
One more thing… Lovable now builds with GPT-6 Sol.
On our 0-to-1 building benchmark it scores 6 to 12% higher than GPT-5.6 Sol at every effort level. The biggest gains are in following the brief, 10 to 15% higher on intent alignment, and in design fundamentals, 8 to 10% higher.
Starting today, builds in Lovable are faster, without any drop in quality.
Lovable now builds with Opus 5.5.
Same quality as Opus 5 on 0-to-1 building and iterative code fixing, at up to 48% fewer steps on existing codebases. It's also more disciplined about checking its own
