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.

1 articlesEvery article links to its raw data

FilteredNvidiaClear filter

1 articles

SortNewest Oldest

EmpiricalAugust 30, 2026

How good are NVIDIA's model scores compared to other models

We tested two free NVIDIA models on 42 Indonesian slang questions. Nemotron Super, 120 billion parameters, answered 34 correctly; Nemotron 3.5 Lightning answered 26; both still trail Gemma at 31 billion parameters, priced at pocket change.

Benchmark Nvidia Model gratis Slang

34/42Nemotron Super26/42Nemotron 3.541/42Gemma 4 31B