Skip to content
AI & Machine Learning Rich #scaling-laws#chinchilla#kaplan

Scaling Laws: Chinchilla vs Kaplan

Loss as a power law in params, data, compute. Chinchilla redrew the optimal frontier.

A free, animated scaling laws: chinchilla vs kaplan you can read here or embed on any website, from Scrollchart.

Scaling Laws: Chinchilla vs Kaplan

Scaling Laws: Chinchilla vs KaplanLoss vs compute (FLOPs, log scale). Chinchilla optimal frontier beats Kaplan at every budget.10^2110^2210^2310^2410^2510^262.53.03.54.0Cross-entropy lossCompute budget (FLOPs)Kaplan 2020Chinchilla 2022

Loss vs compute on log-log axes. Kaplan 2020 frontier (favoring more params) and Chinchilla 2022 frontier (roughly 20 tokens per param) overlaid. GPT-3, Chinchilla, Llama, GPT-4 plotted as points. Compute-optimal contour for a given budget shown as the iso-FLOPs surface.

Good for

  • Pretraining strategy articles explaining why Llama and Mistral overtraining is rational
  • Compute economics content comparing cost-per-quality across model families
  • ML course material on why the Chinchilla paper changed industry training practice

Source & accuracy

This scaling laws: chinchilla vs kaplan is an editorial illustration built to represent the concept accurately. Where it shows figures, they are typical or representative values chosen to make the relationship clear, not a single underlying dataset. The diagram and its explainer are reviewed and maintained centrally, and updated over time as understanding improves.

The power-law relationship between model size and performance

Scaling laws describe how model loss improves as you increase parameters, training data, or compute. The relationship is predictable: loss decreases as a power of the scale factor. Doubling model size does not halve the loss; instead, loss drops by a consistent fraction (typically around 15-20%). This pattern holds across diverse architectures and domains, suggesting it captures something fundamental about learning in high dimensions. The Kaplan scaling laws, derived from GPT-3 experiments, established these relationships empirically and made it possible to predict the loss of a model you have not yet trained.

Chinchilla's reallocation of compute toward data

The original Kaplan scaling laws suggested compute should be split unevenly: roughly 2x more toward data than toward model size for optimal performance. Chinchilla research in 2022 re-examined this question and found the optimal split was much closer to even: parameters and data tokens should scale roughly equally for a fixed compute budget. This meant contemporary models like GPT-3 were actually undertrained relative to their size. The insight redirected the field toward models with more data per parameter, improving sample efficiency and final performance. Chinchilla and its successor Gopher demonstrated that more careful allocation of compute produces smaller, more capable models.

Embed this diagram

Add this animated scaling laws: chinchilla vs kaplan to your own site. Copy one line of HTML, or use the embed builder for theme and sizing options.

Reference

What this is
A free, embeddable, animated scaling laws: chinchilla vs kaplan for any website.
Who uses it
AI/ML blogs, Science popularizers.
How to embed
Copy one line of HTML. No signup. No watermark. Works in WordPress, Webflow, Ghost, Substack, plain HTML.
File size
iframe embed, ~80 KB gzipped (loads on demand, does not block your page paint).
License
Free forever. Editorial explainer text included; updated centrally over time.

Embed format options

Copy the universal HTML snippet, the WordPress shortcode, or an iframe fallback - see the WordPress plugin page for details. Any format keeps the same Core Web Vitals profile and the same explainer text.

Embed snippet
<div data-scrollchart="scaling-laws" data-scrollchart-v="1"></div>
<script src="https://scrollchart.com/embed.js" async></script>

Frequently asked questions

Where can I get a free animated "Scaling Laws: Chinchilla vs Kaplan" for my website?
Scrollchart provides "Scaling Laws: Chinchilla vs Kaplan" as a free, embeddable animated diagram you can add to any website with one line of HTML. No signup is required and there is no watermark. The diagram and its explainer text are served from scrollchart.com, so the embed stays current without any maintenance on your end.
How do I embed a scaling laws: chinchilla vs kaplan in a developer or tech blog?
Copy the one-line snippet from the Scrollchart diagram page and paste it into your post HTML. It works in any static site generator, CMS, or hand-coded HTML page. The embed is a thin loader, not an iframe, so the content is fully in your DOM.