JevMade hello@JevMade.com
← Back to experiments

Benchmarks & research

Jevsus

3,608 one-subject-swapped statements put to Jev as forced true/false picks, in three wordings and eleven languages, with every raw answer published.

Source screenshot of Jevsus
SOURCE SCREENSHOT · source ↗ · captured 2026-09-24Full screenshot ↗

What it does

The authors report that 45% of statements move by 0.20 or more between their three wordings, so those rows are marked range_wide and may be ranked but not quoted.

Maker-reported (not independently measured by JevMade): 3,608 statements, each in 3 wordings · about 210,000 calls, $3.13, 0 errors, 8/8 anchors at 0.00 / 1.00 in every column · 190 sentences, 3,608 statements, 40 forced picks, 34 categories

Primitives
choice, noul
Platform
Python
Added
Project created

Source checked 2026-09-24 — opened the GitHub repository directly.