MLX Benchmark
github.com/goekdeniz-guelmez/mlx-benchmark- Category
- Developer Tools
- Pricing
- Open Source
- Type
- TOOL
- Builder
- @ActuallyIsaak
- GitHub
- 37 stars
- Added
- Jun 18, 2026
About
A specialized benchmarking tool for evaluating Large Language Models on Apple's MLX framework knowledge and coding tasks. It includes 441 questions across different categories and difficulty levels, supports multiple LLM providers (local and cloud), and generates detailed performance reports.
Why it made the leaderboard
Benchmarks how well an LLM actually knows Apple's MLX framework: 441 questions across QA, coding, and debugging, runnable against local Ollama models or OpenAI, Anthropic, and Groq, with detailed reports. Useful for picking which model to trust with MLX work.
Tags
mlxbenchmarkllmapplemachine-learningclievaluation
Tech Stack
Python
Comments (0)
No comments yet
Indexed by a proprietary survey. Corrections welcome.