Run · circles · Jun 2026

Deepseek Pro v4

58.2 / 100 composite

all-DeepSeek · completed Jun 27, 2026

1,041 reqs · 2h 35m

Cleanest tool execution — 0.0% failure rate across 1,041 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.