Across 14 shared benchmarks, A.X-K2 scores higher on 3 and Quasar 438B on 11. The widest gap is TauBench V3 - Banking, where Quasar 438B scores 28.7 against 16.1.
Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.