MethodologyAnnotator qualityUpdatesHugging Face434.9k downloadsSuggest a model or benchmarkRequest a private benchmark
Benchmarks
Dimensions
License
Models
Categories
Output Type
Style & Composition
Subject
SVG v1updated 2026-08-20

The Human-Preference Leaderboard for SVG Generation

Rapidatabenchmark@rapidata.ai

Abstract

This benchmark ranks SVG generation models using human comparisons of outputs generated from the same prompt. We curated 500 prompts across 9 categories focusing on commercial applicability and ensuring reproducibility of the results. The rankings are updated continuously from 4,264,127 responses across 1,010,468 pairwise human-preference matches. Each match is decided by a majority of at least three responses. All data and judgments are public; see the methodology for details on evaluation and scoring.

LeaderboardCompare OutputsMatchupsAnalysis· DemographicsPromptsDetails

Top model by region

We use crowd intelligence to deliver real, diverse human feedback at scale for model evaluation and post-training.

Benchmarks
Text-to-ImageOutput Diversity (Mode Collapse)Multi-Step Image Editing (Identity Drift)Camera MovementRelative Camera MovementPhysicsPhysicsRealismImage-to-3DSVGLLM-to-3DSuggest a model or benchmark
Method
MethodologyData on Hugging Face
Rapidata
rapidata.ai Private benchmarksContactX LinkedIn
Rapidata, benchmark.ai © 2026