Insight

How far can AI and our own language tools be trusted?

We test our own correction engine and various outside AI models against Indonesian and regional languages, then publish the numbers as they are. On this page, we sum up each finding in a single picture. The full method and raw data are one click away on every card.

1 findingsEvery finding links to its technical version
FilteredModel costClear filter

1 findings

AI benchmarkEmpirical
Gemini 2.5 Flash
1.0
Gemini 3.1 Flash Lite
1.0
DeepSeek V3.2
1.9
Gemma 4 31B
1.9
Qwen 3.5 Flagship
726.0
Kimi K2.6
733.1
Qwen3 235B
875.8
Output tokens per single-letter answer

Asked for a Single Letter, One AI Used 876 Times More Tokens

We asked 7 AIs to answer with a single letter, whether A, B, C, or D. The most wasteful AI used 876 times more tokens than the most frugal, for the exact same work.

November 17, 2026 · 3 menit bacaRead the finding →