Across 30 shared benchmarks, Gemini 3.6 Flash scores higher on 2 and Gemini 3.8 Flash on 28. The widest gap is OSWorld 2.0, where Gemini 3.8 Flash scores 59 against 33.8.
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.