Favur Evals
favur.dev

Model · Google

Google Gemini Flash 3.5

8 appearances · meta-score 59.9/100 · last seen 2026-07-16 · scored under rubric v15

Pooled composite across 8 primary runs: 62.7 ± 12.5 (95% CI)

Agent role scores

Per-agent-role scores for Google Gemini Flash 3.5
Agent roleScore / 10
Develop Agent8.10
Orchestrator7.89
Spec Agent7.11
Sprint-Plan Agent6.70
Test Agent6.22
Scout Agent6.17
Platform Agent5.70
Code-Review Agent5.40
Sprint-Review Agent5.26
Code Agent5.03
Build Agent4.98
Architect4.92
Pseudocode Agent4.92

Run history (primary model)

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.