Highest AI score in the SAT

The highest score in the SAT exam by an artificial intelligence is 1410 out of 1600, which was achieved in March 2023 by the GPT-4 Large Language Model, built by OpenAI (USA). The score puts GPT-4 ahead of 94% of the humans that have taken the test, which is used as an admissions test by universities in the United States.

OpenAI's GPT-4 is a type of artificial intelligence called a Large Language Model (or LLM). These consist of a deep-learning neural network that has been trained on a massive quantity of written material, typically trillions of words scraped from the internet and other sources.

The training process involves the neural network cycling through text data sets, gradually learning the relationships between various words and phrases in a probabilistic manner (i.e. in the context of the prompt Z, word X is most likely to be followed by word Y). LLM's base these decisions by weighing an enormous number of factors (GPT-4 may have more than 1 trillion parameters that inform its text generation).

With enough training data, and enough time and processing power (it has been estimated that GPT-4 cost $60–$100 million to train) this approach can create a believable impression of intelligence. The problem with this method of constructing artificial intelligence is that the reasoning behind the AI's decisions is entirely obscured, even to its developers. This is a particular problem in the context of a phenomenon known as "hallucination", in which LLM's provide wildly inaccurate or misleading responses that are seemingly generated spontaneously.

Interestingly, while GPT-4 performed well in rigid test environments such as the SAT, it performed very poorly in tests that required a significant degree of creative thought. It managed only 2 out of 5 in Advanced Placement English Language and Composition (a test typically taken by high school students) and just 3 out of 45 in the creative coding test called Leetcode.