About
Every new AI model ships with a page of benchmark scores. Humans don't get one. Brain Benchmark is our attempt at that page: a set of short, standardised exercises that each isolate one thing a human mind can do, and measure it honestly.
There are 21 tests across 7 capabilities. Each takes one to a few minutes, needs no account, and puts your result on a live leaderboard next to everyone else's. Over time your results build a capability profile — a map of where you are strong and what to test next.
Reaction Time and Aim Trainer descend from the oldest measurement in psychology: how long it takes to turn a stimulus into a response. Simple reaction time is one of the most reliable individual-difference measures there is.
Jensen, A. R. (2006). Clocking the Mind: Mental Chronometry and Individual Differences. Elsevier.
Number Memory is a digit-span task; Visual, Sequence and Chimp tests probe visuospatial and serial-order memory. Verbal Memory uses continuous recognition — deciding, word by word, whether you have seen it before.
Miller, G. A. (1956). The magical number seven, plus or minus two. Psychological Review, 63(2), 81–97. · Shepard, R. N. (1967). Recognition memory for words, sentences, and pictures. JVLVB, 6(1), 156–163. · Inoue, S., & Matsuzawa, T. (2007). Working memory of numerals in chimpanzees. Current Biology, 17(23), R1004–R1005.
The Stroop and Flanker tasks measure how well you hold a goal while something else pulls at your attention — conflicting word meaning in one, conflicting neighbours in the other. Flanker reports your "interference cost" directly. Object Tracking is multiple object tracking: following several identical moving dots at once, a test of how many things your attention can hold.
MacLeod, C. M. (1991). Half a century of research on the Stroop effect. Psychological Bulletin, 109(2), 163–203. · Eriksen, B. A., & Eriksen, C. W. (1974). Effects of noise letters upon the identification of a target letter. Perception & Psychophysics, 16(1), 143–149. · Pylyshyn, Z. W., & Storm, R. W. (1988). Tracking multiple independent targets: Evidence for a parallel tracking mechanism. Spatial Vision, 3(3), 179–197.
Color Perception is a staircase: the shade difference shrinks until you can no longer resolve it. Time Estimation measures interval timing — how accurately you can reproduce a duration with no clock to look at.
Grondin, S. (2010). Timing and time perception. Attention, Perception, & Psychophysics, 72(3), 561–582.
Mental Rotation is a 2D version of the Shepard–Metzler task, where response time grows with the angle you must rotate through — we show you that "rotation cost". Tangrams, Maze and Sudoku add planning and deduction.
Shepard, R. N., & Metzler, J. (1971). Mental rotation of three-dimensional objects. Science, 171(3972), 701–703. · Uttal, D. H., et al. (2013). The malleability of spatial skills. Psychological Bulletin, 139(2), 352–402.
Arithmetic, Algebra and Geometry are sudden-death fluency tests: accuracy first, then speed. They lean on learned knowledge as well as raw processing, which makes them the most trainable tests on the site.
Fluency-based math measures are standard in educational assessment; ours are not normed against a reference population.
Typing Test measures words per minute with accuracy; Word Search measures how quickly you can find and spell words in a field of letters.
WPM is computed as correct characters ÷ 5 per minute, the convention used by most typing benchmarks.
How scores work
Limits — please read