Measured Collection

Research

We test how well AI actually understands Indonesian and its regional languages, map the words that trip up native speakers, and publish the numbers along with the raw data and their limits, including when the results are not what we hoped for.

1 articlesEvery article links to its raw data

FilteredModel costClear filter

1 articles

SortNewest Oldest

EmpiricalAugust 5, 2026

Seven AI models tested on a single letter answer with an 876-fold token gap

Seven models tested on one and the same set. An 876-fold gap in output tokens for a single letter answer, and the numbers themselves move between runs.

AI benchmark Model cost Methodology

875.8Tokens, most wasteful model1.0Tokens, leanest model876xGap on the same set