Run · circles · Jun 2026

Glm 5.2

61.5 / 100 composite

all-Z.ai · completed Jun 28, 2026

1,251 reqs · 3h 47m

Cleanest tool execution — 0.0% failure rate across 1,251 requests.

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.