Skip to content
AI & Machine Learning Medium #eval-suites#benchmarks#mmlu

LLM Eval Suites Compared

MMLU, GSM8K, HumanEval, MATH, BBH, ARC. What each measures and where they saturate.

A free, animated llm eval suites compared you can read here or embed on any website, from Scrollchart.

LLM Eval Suites Compared

LLM Eval Suites ComparedMMLU, GSM8K, HumanEval, BBH, GPQA across frontier models; saturated axes flagged25%50%75%saturation thresholdKnowledgeMMLU / MMLU-ProMathGSM8K / MATHCodeHumanEval / SWECommonsenseARC / HellaSwagMulti-stepBBH / GPQAMultilingualMGSM / X-MMLUModelsGPT-4oClaude 3.5Gemini UltraGPT-3.5 (older)Saturation concernMMLU 5-shot: GPT-4 class near88-92%; MMLU-Pro extends rangeHarder successorsMMLU-Pro, GPQA Diamond, LiveBenchFrontier models near-saturate MMLU and GSM8K; multilingual and multi-step reasoning remain the differentiating axes

A radar chart with 6-8 axes (knowledge, math, code, commonsense, multi-step reasoning, multilingual). Several frontier models plotted. Saturation points and contamination concerns annotated. New harder benchmarks (MMLU-Pro, GPQA) shown extending the dimensions.

Good for

  • AI research literacy articles explaining why leaderboard scores mislead when benchmarks saturate
  • Model selection guides comparing capability profiles across frontier systems
  • Content covering the transition from MMLU-era to GPQA-era evaluation standards

Source & accuracy

This llm eval suites compared 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.

Benchmark diversity and saturation

Machine learning benchmarks are the most studied datasets in the field. MMLU (Massive Multitask Language Understanding) covers 57 subjects in multiple-choice format. GSM8K has middle-school math word problems. HumanEval tests code generation. MATH has competition-level problems. BBH (Big Bench Hard) is a collection of hard reasoning tasks. ARC is a set of science questions.

Each benchmark has different characteristics. MMLU tests breadth of knowledge; HumanEval tests coding ability; MATH tests mathematical reasoning. A model can excel on one and fail on another. No single benchmark tells the whole story. Modern LLM papers report performance on many benchmarks to show capability across different domains.

Saturation and the scaling plateau

As models improve, benchmarks eventually saturate: performance approaches 100% and stops improving. MMLU, once a separating benchmark, is now saturated by large frontier models (90%+ performance). HumanEval, too, has seen ceiling effects at scale. MATH and other hard reasoning tasks show more separation between models but are also starting to saturate.

Saturated benchmarks lose discriminative power. If benchmark A is 95% saturated and benchmark B is 50%, then B is more informative for ranking models. Researchers constantly need new benchmarks to distinguish progress. This arms race between models and benchmarks is necessary but creates an incentive for overfitting to specific benchmarks. The broader lesson: no single metric or benchmark fully captures model capability. Real-world performance often diverges from benchmark rankings, especially for tasks unlike the benchmark's distribution.

Embed this diagram

Add this animated llm eval suites compared 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 llm eval suites compared 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="eval-suites-comparison" data-scrollchart-v="1"></div>
<script src="https://scrollchart.com/embed.js" async></script>

Frequently asked questions

Where can I get a free animated "LLM Eval Suites Compared" for my website?
Scrollchart provides "LLM Eval Suites Compared" 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 llm eval suites compared 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.