Across 14 shared benchmarks, Apodex 1.1 scores higher on 12 and K-EXAONE 2.0 on 2. The widest gap is critpt, where Apodex 1.1 scores 4.6 against 0.9.
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.