Favur Evals
favur.dev

Model · Google

Google Gemini Flash 3.6

5 appearances · meta-score 72.3/100 · last seen 2026-07-24 · scored under rubric v15

Pooled composite across 5 primary runs: 64.6 ± 10.5 (95% CI)

Agent role scores

Per-agent-role scores for Google Gemini Flash 3.6
Agent roleScore / 10
Code-Review Agent8.66
Architect8.36
Sprint-Review Agent8.34
Develop Agent8.13
Orchestrator7.81
Director7.41
Platform Agent7.01
Build Agent6.82
Test Agent6.80
Spec Agent6.61
Scout Agent6.48
Code Agent6.22
Sprint-Plan Agent6.05
Pseudocode Agent4.90

Run history (primary model)

Runs where Google Gemini Flash 3.6 was the primary model, oldest first
RunSoWDateComposite
Gemini Flash 3.6circlesJul 202673.2
Gemini Flash 3.6 + Gemini Flash LitecirclesJul 202672.1
Gemini Flash 3.6 + Gemini Flash LitesolarSystemJul 202663.8
Gemini Flash 3.6 + Gemini Flash Litethe2048Jul 202652.6
Gemini Flash 3.6circlesJul 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.