Measured Collection

Articles

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.

2 articlesEvery article links to its raw data

FilteredOpenaiClear filter

2 articles

SortNewest Oldest

EmpiricalSeptember 11, 2026

GPT-6 Astra and Luna tie on Indonesian slang items

GPT-6 Astra scored 42 of 42 on the public half of our Indonesian slang benchmark, the joint best result in the panel. Counting the 18 withheld items too, it finished 59 of 60, 1 behind OpenAI's own cheaper GPT-5.6 Luna. 1 item apart on 60 is not a statistically meaningful gap, and that is the more interesting finding: the public half no longer separates the strongest models at all.

Benchmark Openai Slang Held out

42/42Astra public59/60Astra total$0.15Astra cost

EmpiricalSeptember 7, 2026

OpenAI's GPT-6 Astra Scores Below Its Own Cheaper Model on Rare Javanese Words

GPT-6 Astra, OpenAI's newest and most expensive model, answered 33 of 43 rare Javanese words correctly, behind Google's Gemini 3.5 Flash (40/43) and OpenAI's own cheaper GPT-5.6 Luna (35/43), at 56 times Luna's cost. On a separate Javanese speech-level test, Astra tied Gemini 3.5 Flash for the best score in the panel.

Benchmark Openai Google Javanese

$0.22Astra cost76.7%Astra score93.0%Gemini score

About

We measure what AI can and cannot do with Indonesian, then publish the numbers together with the raw data and the limits of what they show.

2 articles published

Trust labels

Who writes this

M. Khoirul Huda

Fullstack engineer. I build the dictionary and the tooling on this site myself, so when something is wrong, that is on me too. Every article links to its raw data so you can check it yourself.

mkhuda.com