---
title: MLX Benchmark V2 Leaderboard
emoji: 🍎
colorFrom: yellow
colorTo: gray
sdk: gradio
sdk_version: "5.29.0"
app_file: app.py
pinned: true
tags:
  - leaderboard
  - benchmark
  - mlx
  - apple-silicon
  - eval:mlx
  - test:public
  - judge:auto
license: mit
short_description: "Evaluating LLMs on Apple MLX framework"
---

# 🍎 MLX Benchmark V2 Leaderboard

Evaluating LLM proficiency on Apple's **[MLX](https://ml-explore.github.io/mlx/)** machine learning framework.

**520 questions** · **11 categories** · **6 question types** · **4 difficulty levels**

## Features

- 🏅 **Interactive leaderboard** with search & column filtering
- 📊 **Visual charts** — overall comparison, difficulty breakdown, category radar
- 📝 **Full documentation** of the benchmark methodology
- 📨 **Submit your own results** to be included

## Links

- **Dataset:** [Goekdeniz-Guelmez/MLX-Benchmark-V2](https://huggingface.co/datasets/Goekdeniz-Guelmez/MLX-Benchmark-V2)
- **CLI:** `pip install mlx-benchmark` → `mlx-bench --model <model>`
- **GitHub:** [Goekdeniz-Guelmez/MLX-Benchmark](https://github.com/Goekdeniz-Guelmez/MLX-Benchmark)
- **Paper:** [Gabliteration (arxiv:2512.18901)](https://arxiv.org/abs/2512.18901)

Created by [Gökdeniz Gülmez](https://huggingface.co/Goekdeniz-Guelmez)