Quick Keypoints
- Evaluates over 230 language models on vector code generations.
- Measures ability to compile valid SVG portraits of Gary Busey.
- Compares coding accuracy, file sizes, and API generation costs.
- Updates leaderboards dynamically as new language models release.
What is BuseyBench?
SVG vector drawing evaluation benchmark for language models.
BuseyBench is a free benchmarking resource and leaderboard that evaluates how well LLMs write valid SVG image code.
Who Needs BuseyBench?
AI research engineers, model developers, and software programmers.
Primary Use Cases
- Autocompleting code syntax and logic blocks in real-time.
- Explaining complex functions and debugging codebase errors.
- Generating boilerplate code and unit test suites automatically.
Important Features
- Model Comparison: Ranks models on SVG drawing tasks using gpt-4o benchmarks.
- SVG Code Check: Evaluates whether output SVG tags are syntactically valid.
- Cost Analysis: Tracks token costs vs quality of the compiled vector files.
Current Updates About BuseyBench
- BuseyBench added support for evaluating Claude 3.5 Sonnet and Gemini 1.5 Pro models
- Current Version: BuseyBench v1.0
Alternatives to BuseyBench
If you want to check similar software, these alternative tools offer comparative features:
Editorial Rating
4.6 / 5.0
Pricing Plans
| Plan | Price |
|---|---|
| FreeAccess to full SVG leaderboard and database benchmark files | $0 |