Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)
Source
Sebastian Raschka, PhD
Author
Sebastian Raschka, PhD
Date
Key takeaways · AI-distilled
The four evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → methods fall into two families. benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition →-based ones (multiple choice, verifiers) grade against a fixed answer key; judgment-based ones (leaderboards, LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → judges) grade on someone's preference, whether human voters or another model.
MMLU spans 57 subjects and about 16,000 multiple-choice questions, scored as plain accuracy: 14,000 right out of 16,000 is 87.5%. It measures knowledge recall the way a standardized test does.
One MMLU number can be computed several ways: compare the generated answer letter against the key, or score the log-probability the model assigns to each choice. Two reported MMLU accuracies aren't automatically comparable.
Prompt shape is part of the measurement. The prompt ends with 'Answer: ', trailing space included, to push the model toward emitting a single letter next. Few-shot examples (5-shot MMLU) were once needed; today's base models manage without.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Why it matters
It gives a hands-on, from-scratch breakdown of the four main LLM evaluation approaches — including how MMLU scoring and verifier-based evals actually work — so you can critically interpret benchmarks and leaderboards instead of taking headline numbers at face value.
Key quotes
“One of the reasons why judges work so well is also that evaluating an answer is often easier than generating one.”
“Unfortunately, there is no single best method since, as we have seen, each comes with different trade-offs.”
“the best evaluation combines multiple areas. But ideally it also uses data that directly aligns with your goals or business problems.”
