Model · Google

Google Gemini Flash Lite 3.5

1 appearance · meta-score 71.0/100 · last seen 2026-07-21 · scored under rubric v15

Pooled composite across 1 primary run: 78.2 — no interval, a single run proves nothing about spread provisional: n < 3, treat as unsettled

$2.60Total cost
20,342,383Tokens
76.3%Cache hit
462Requests
0.43%Failure rate
1.00Tools/response
7,826,033Tokens per $

Agent role scores

Per-agent-role scores for Google Gemini Flash Lite 3.5
Agent role	Score / 10
Develop Agent	8.31
Sprint-Review Agent	8.29
Orchestrator	7.84
Build Agent	7.82
Code-Review Agent	7.68
Scout Agent	7.12
Test Agent	6.72
Code Agent	6.56
Platform Agent	6.55
Spec Agent	6.09
Pseudocode Agent	5.59
Sprint-Plan Agent	5.57

Run history (primary model)

Runs where Google Gemini Flash Lite 3.5 was the primary model, oldest first
Run	SoW	Date	Composite
Gemini Flash Lite 3.5	circles	Jul 2026	78.2

Also in the roster of

Gemini Flash 3.6 + Gemini Flash Lite
Gemini Flash 3.6 + Gemini Flash Lite
Claude Sonnet 5 + Gemini Flash Lite
Gemini Flash 3.6 + Gemini Flash Lite

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.