# SVGBench

SVGBench is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Tests whether language models can generate SVGs that satisfy requirements involving knowledge, code, instructions, and physical reasoning.

## Details

- Address: Online, Global
- Website: [github.com/johnbean393/SVGBench](<https://github.com/johnbean393/SVGBench>)
- Tags: Viral, Science
- Category: Multimodal
- Status: Active
- Data licence: unknown
- Data access: open
- Grader: llm-judge
- Organization: John Bean
- Released: 2025-07
- Leaderboard: [github.com/johnbean393/SVGBench](<https://github.com/johnbean393/SVGBench>)
- Repository: [github.com/johnbean393/SVGBench](<https://github.com/johnbean393/SVGBench>)
- Top-score provenance: lab self report
- Top score: 75.6%
- Top-score source: [github.com/johnbean393/SVGBench](<https://github.com/johnbean393/SVGBench>)
- ABI family: No

## Questions

### Where is SVGBench?

SVGBench is at Online, Global.

### How do I contact SVGBench?

To contact SVGBench, visit https://github.com/johnbean393/SVGBench.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/svgbench>)
- [Multimodal in Online](<https://aibenchmarkindex.com/global/online/category/multimodal.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.