Verbal fluency task

View original ↗

At a glance

Tests
Verbal fluency (Generation): producing many fitting words quickly under a rule.
How
Name as many words as possible from one category, such as animals, in one minute. Usually spoken; here typed.
Best AI
n/a
Humans
—
Our items
3
Generation gap, overall
-34.9

Example item

A specimen written for this page. Live items are similar but never shown, so posted answers can't spoil them.

Name the animalsspecimen · not scored

Type as many different animals as you can in 60 seconds, pressing Enter after each.

(a) Typed in 60 seconds

foxcameleaglecamelunicornsalmon
Figure 1. A category fluency item. Repeats and words outside the category don't count. Benchmark: Verbal fluency task. Answer: Four count here: fox, camel, eagle, salmon. The second camel is a repeat and a unicorn isn't an animal on our list.

Human vs AI

What the benchmark reports, and where the faculty stands overall

Best published AI

n/a

untimed listing is trivial for language models

Thurstone (1938) ↗

Humans

—

This benchmark doesn't report a human figure.

Generation overall · faculty reference, 0–100

Measured on other tests, not on Verbal fluency task.

Human ref.
50.0
Best AI
84.9

Human: GDPval, expert vs expert (parity by design). AI: GDPval wins or ties, GPT-5.5 (vendor-reported).

How we mirror it

Three categories with lists we can check: animals, countries, and fruits and vegetables. One minute each; type a word and press Enter.

Each word is checked against the list, ignoring capitals, accents and plurals; repeats count once. Typing is slower than speaking, so the pass marks are provisional until our own data sets them.

Items are original, versioned, and assigned at random, so a posted answer spoils only one variant.

What we record

different valid wordsrepeatswords not in the listtime of each wordpastestab switches