Skip to main content
VerdictAI Benchmark
Back to Leaderboard
N

Nanbeige4.1-3B

Open Weight

Provider: Nanbeige • ID: nanbeige4-1-3b

Detailed evaluation metrics and judge breakdown for Nanbeige4.1-3B across all 4 launch categories.

Compare in Blind Arena
Pricing: In — • Out —
Composite Verdict Score
11.1
0
.
0
/100

Category Score Breakdown

Frontend UI11.3

Interactive dashboards and landing pages

Game Dev10.9

Canvas 2D physics and browser games

SVG Art11.2

Vector graphics and generative math art

Agentic Tasks10.8

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
11.4
Craft— Clean semantic markup and clean TypeScript
11.2
Design— Visual aesthetics, contrast, layout harmony
11.0
Creativity— Original micro-interactions and layout depth
10.8
Fidelity— Strict adherence to complex prompt constraints
10.9