Skip to main content
VerdictAI Benchmark
Back to Leaderboard
A

Olmo 3.1 32B Instruct

Open Weight

Provider: Allen Institute for AI • ID: olmo-3-1-32b-instruct

Detailed evaluation metrics and judge breakdown for Olmo 3.1 32B Instruct across all 4 launch categories.

Compare in Blind Arena
Pricing: In — • Out —
Composite Verdict Score
6.5
0
.
0
/100

Category Score Breakdown

Frontend UI6.6

Interactive dashboards and landing pages

Game Dev6.3

Canvas 2D physics and browser games

SVG Art6.5

Vector graphics and generative math art

Agentic Tasks6.3

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
6.7
Craft— Clean semantic markup and clean TypeScript
6.5
Design— Visual aesthetics, contrast, layout harmony
6.4
Creativity— Original micro-interactions and layout depth
6.3
Fidelity— Strict adherence to complex prompt constraints
6.3