Demo Project

AI Model Comparison

10 LLMs compared on benchmarks, cost, and speed. Interactive CLI recommender matches models to use cases with paid vs free alternatives.

Key Metrics

10
Models (LLM + Image)
8
Use Cases
Interactive
CLI Recommender

Static Output

AI Model Comparison chart

Quad-chart: benchmark scores grouped by model, composite score by provider, cost vs performance scatter, and paid vs free comparison.

Interactive Recommender CLI

Run the interactive CLI:

python ai_model_comparison.py

Answer 3 questions: (1) What kind of task? (2) Budget? (3) Need open source? Get a ranked recommendation with platform info.

Coding
Claude 3.5 Sonnet (paid) or Mistral Large (free)
Image Generation
DALL-E 3 (paid) or Stable Diffusion 3.5 (free)
Content Creation
GPT-4o (paid) or Llama 3 70B (free)
Data Analysis
Claude 3.5 Sonnet (paid) or Mistral Large (free)

Platforms

Where to access each model:

GPT-4o
OpenAI API | ChatGPT (chatgpt.com)
Claude 3.5 Sonnet
Anthropic API | Claude (claude.ai)
Llama 3 70B (free)
Groq | Replicate | Hugging Face Chat
Mistral Large (free)
Mistral API | Le Chat (chat.mistral.ai)
Stable Diffusion 3.5 (free)
Hugging Face | Replicate | Self-host
FLUX.1 (free)
Replicate | Hugging Face Spaces

Notebook

Explore the full comparison with benchmark breakdowns in Jupyter Notebook.

Download .ipynb Notebook

Tech Stack

Python Pandas NumPy Matplotlib Plotly
View Repository Download Script Architecture Getting Started Interactive Chart

Tip: Run python ai_model_comparison.py for an interactive session that asks about your use case and recommends models with platforms.