Skip to main content
Back to Leaderboard
Google logo

Gemini 2.5 Flash Preview (Sep '25) (Reasoning)

Provider: Google • ID: gemini-2-5-flash-preview-09-2025-reasoning

Detailed evaluation metrics and judge breakdown for Gemini 2.5 Flash Preview (Sep '25) (Reasoning) across all 4 launch categories.

Compare in Blind Arena
Pricing: In — • Out —
Composite Verdict Score
23.8
0
.
0
/100

Category Score Breakdown

Frontend UI24.3

Interactive dashboards and landing pages

Game Dev23.3

Canvas 2D physics and browser games

SVG Art24.0

Vector graphics and generative math art

Agentic Tasks23.1

Multi-step execution planning

Auditable Multi-Judge Dimension Scoring

Grades evaluated across 3 independent judge models using published rubrics.

Functionality— Executes without runtime JS exceptions
24.5
Craft— Clean semantic markup and clean TypeScript
24.0
Design— Visual aesthetics, contrast, layout harmony
23.6
Creativity— Original micro-interactions and layout depth
23.1
Fidelity— Strict adherence to complex prompt constraints
23.3