@huuw_khoa benchmarks Jev against Gemma 4 12B and gpt-oss-20b on 60 knowledge-graph questions in open-source hopwise.

Benchmark note. Asks whether a typed-decision model walks a knowledge graph better than a general LLM; tries Jev, Gemma 4 12B and gpt-oss-20b on 60 questions and links github.com/Aohkne/hopwise. For researchers comparing System One models to LLMs on graph traversal.