DeepSeek R1 (Jan '25)
Open WeightProvider: DeepSeek • ID: deepseek-r1-0120
Detailed evaluation metrics and judge breakdown for DeepSeek R1 (Jan '25) across all 4 launch categories.
Compare in Blind Arena
Pricing: In $1.68 per 1M tokens • Out $4.70 per 1M tokens
Composite Verdict Score/100
18.5
0
.0
Category Score Breakdown
Frontend UI18.9
Interactive dashboards and landing pages
Game Dev18.1
Canvas 2D physics and browser games
SVG Art18.7
Vector graphics and generative math art
Agentic Tasks18.0
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
19.1
Craft— Clean semantic markup and clean TypeScript
18.7
Design— Visual aesthetics, contrast, layout harmony
18.3
Creativity— Original micro-interactions and layout depth
18.0
Fidelity— Strict adherence to complex prompt constraints
18.1