AnalysisAI ModelsJuly 26, 2026

Kimi K3 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing

904 DeepSWE rollouts: Sol leads pass@1; Kimi K3 wins pass@4 at 2.8x the solves per dollar. Routing between them reaches ~85.6%.

1 source

More stories today

Open the live feed