Favur Evals
favur.dev

Vendor

Z.ai

1 model version evaluated ·3 runs in the corpus · rubric v15 · Z.ai site ↗

Model versions

Model versions from Z.ai
ModelMeta-scoreAppearancesBest atLast seen
Z.ai Glm 5.269.93Sprint-Review Agent2026-07-17

Runs (primary model)

Runs where a Z.ai model was primary, ranked by composite
RunSoWDateComposite
Glm 5.2circlesJul 202661.6
Glm 5.2circlesJul 202654.5
Glm 5.2circlesJun 202646.9

Every run on Favur Evals is scored by the same deterministic engine, on the same Statements of Work. The benchmark is self-funded — no vendor sponsorship, credits, or grants.