Vendor

xAI

1 model version evaluated ·4 runs in the corpus · rubric v15 · xAI site ↗

Model versions

Model versions from xAI
Model	Meta-score	Appearances	Best at	Last seen
xAI Grok 4.5	72.5	4	Sprint-Review Agent	2026-07-22

Runs (primary model)

Runs where a xAI model was primary, ranked by composite
Run	SoW	Date	Composite
Grok 4.5	circles	Jul 2026	64.7
Grok 4.5	circles	Jul 2026	63.2
Grok 4.5	circles	Jul 2026	62.3
Grok 4.5	circles	Jul 2026	61.0

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.