Lovable adds GPT-6 Sol and reports 6-12% benchmark gain

Lovable @LovableOriginally posted 2026.09.23

Open original on X

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.