guessed . Can you beat them?
How long will take to ? A person takes about .
Racing GLM-5.2 (Z-AI) against a typical person on translate a paragraph: 6 min by hand versus 2.2 s for the model, 164× faster, 87% accurate on this task's rubric. ✗ Overkill. GLM-5.2 is slower here for no gain — try Gemma 4 31B. It used 115 tokens for a cost of $0.00: see how that stacks up against every other model →
Choose a task and model. Compare its recorded or estimated speed, accuracy, and cost with a typical human time.
guessed . Can you beat them?
How long will take to ? A person takes about .
Run the same task on Claude and GPT side by side.
"You" is a typical time for a person doing the task by hand, unless you've taken the 15-second typing test above, in which case it's your own. "AI" is a recorded run for the selected model, shown to scale. Stage times, accuracy, and token cost are placeholder profiles until runs are recorded and scored. How we measure → · FAQ → · Model comparison → · Open dataset →