Favur Evals
favur.dev

Vendor

Anthropic

2 model versions evaluated ·7 runs in the corpus · rubric v15 · Anthropic site ↗

Model versions

Model versions from Anthropic
ModelMeta-scoreAppearancesBest atLast seen
Anthropic Claude Sonnet 4.643.22Scout Agent2026-07-03
Anthropic Claude Sonnet 566.95Sprint-Review Agent2026-07-23

Runs (primary model)

Runs where a Anthropic model was primary, ranked by composite
RunSoWDateComposite
Claude Sonnet 5circlesJul 202670.8
Claude Sonnet 5 + Gemini Flash LitesolarSystemJul 202658.3
Claude Sonnet 5circlesJul 202657.9
Claude Sonnet 5circlesJul 202647.8
Claude Sonnet 5circlesJul 202646.6
Claude Sonnet 4.6circlesJul 202644.4
Claude Sonnet 4.6circlesJun 202642.3

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.