Skip to main content
VerdictAI Benchmark
Back to Leaderboard
DeepSeek logo

DeepSeek R1 Distill Qwen 14B

Open Weight

Provider: DeepSeek • ID: deepseek-r1-distill-qwen-14b

Detailed evaluation metrics and judge breakdown for DeepSeek R1 Distill Qwen 14B across all 4 launch categories.

Compare in Blind Arena
Pricing: In — • Out —
Composite Verdict Score
9.8
0
.
0
/100

Category Score Breakdown

Frontend UI10.0

Interactive dashboards and landing pages

Game Dev9.6

Canvas 2D physics and browser games

SVG Art9.9

Vector graphics and generative math art

Agentic Tasks9.5

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
10.1
Craft— Clean semantic markup and clean TypeScript
9.9
Design— Visual aesthetics, contrast, layout harmony
9.7
Creativity— Original micro-interactions and layout depth
9.5
Fidelity— Strict adherence to complex prompt constraints
9.6