Across 14 shared benchmarks, Agnes 2.5 Pro Beta scores higher on 12 and K-EXAONE 2.0 on 2. The widest gap is TauBench V3 - Banking, where Agnes 2.5 Pro Beta scores 35.7 against 11.5.
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.