Basics
Benchmark
A standard test used to measure and compare model abilities, such as coding, maths or knowledge.
Benchmarks make comparison possible but are imperfect: models can be tuned toward them, and a high score on one test does not guarantee good results on your task. This site shows scores with their source.
Frequently asked questions
What does Benchmark mean?
A standard test used to measure and compare model abilities, such as coding, maths or knowledge. Benchmarks make comparison possible but are imperfect: models can be tuned toward them, and a high score on one test does not guarantee good results on your task. This site shows scores with their source.