Favur Evals
favur.dev

Vendor

OpenAI

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

Model versions

Model versions from OpenAI
ModelMeta-scoreAppearancesBest atLast seen
OpenAI Gpt Luna 5.664.71Sprint-Plan Agent2026-07-14
OpenAI Gpt Terra 5.665.41Sprint-Plan Agent2026-07-12

Runs (primary model)

Runs where a OpenAI model was primary, ranked by composite
RunSoWDateComposite
Gpt Terra 5.6circlesJul 202661.5
Gpt Luna 5.6circlesJul 202661.1

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.