Benchmarks tested

of 6 benchmarks we publish

This model has been run on every benchmark we publish.

Runs completed

complete runs on record

One run means the model answered every item in a set, start to finish. A set run more than once contributes more than one.

Total cost

$0.0000

for every run above

The real amount billed by the provider, summed, not an estimate from per-token pricing. Not yet divided by correct answers.

Total tokens

65,841

input and output combined

Counted only from runs that recorded tokens. Runs on the older path did not store them, and the figure is not guessed.

How many answers were correct

Each bar is one benchmark: how many items it answered correctly out of every item in that set. We wrote the questions and answer keys ourselves and had them checked by two native speakers, and every model answers exactly the same items.

9 benchmarks

Tingkat tutur bahasa Jawaopen answer5/6 83.3%

Pemahaman slang Indonesia33/42 78.6%

Normalisasi teks Indonesiaquestion version 236/49 73.5%

Normalisasi teks Indonesiaquestion version 335/49 71.4%

Koreksi ejaan Indonesia25/38 65.8%

Tingkat tutur bahasa Jawamultiple choice16/27 59.3%

Normalisasi teks Indonesiaquestion version 123/49 46.9%

Arti kata Jawa sehari-hari60/135 44.4%

Arti kata Jawa langka9/43 20.9%

Share of items answered correctly across 9 benchmarks

How far the cost pays off

This model runs on our own hardware, not through a paid provider, so there is no bill to record. A zero here would make it the cheapest model we have ever tested, and that is not a figure we measured.

Tokens used

Input and output are kept apart because they are priced differently, often tenfold. A long output bar means the model talks a lot, and that is where nearly all the cost difference comes from.

60,198 in, 5,643 out

inputoutput

Tingkat tutur bahasa Jawaopen answer914 · 96

Pemahaman slang Indonesia9,920 · 120

Normalisasi teks Indonesiaquestion version 29,900 · 684

Normalisasi teks Indonesiaquestion version 39,210 · 687

Koreksi ejaan Indonesia9,909 · 184

Tingkat tutur bahasa Jawamultiple choice4,654 · 76

Normalisasi teks Indonesiaquestion version 18,106 · 687

Arti kata Jawa sehari-hari6,228 · 2,594

Arti kata Jawa langka1,357 · 515

Tokens for one full run, per benchmark

Wait time per call

We do record its wait time, but it measures our own machine, not a service anyone else can buy. Putting it on the same chart as hosted models compares two different things, so the figure is not drawn here.

Test coverage

6/ 6

This model has been tested on all 6 benchmarks we publish.

6 of 6 benchmarks we publish

Earlier question versions

The questions or the key changed after these were measured. Kept as history, not as current results.show 2 rows

Pemahaman slang Indonesia21/27 77.8%

Arti kata Jawa sehari-hari60/135 44.4%

Results on an earlier version of the questions or answer key

Log11 calls to this model, spread across 3 days.Open

This model is called through a provider id that may not pin a version, so the dates below state which weights were actually tested. Rows marked with a hyphen have a date we inferred from file history rather than recorded at call time, so we do not show a clock time for them.

17 Aug 20261 runs

22:06Pemahaman slang Indonesiamultiple choice33/42

16 Aug 20261 runs

22:05Arti kata Jawa sehari-hariword meaning60/135

15 Aug 20269 runs

16:57Tingkat tutur bahasa Jawaopen answer5/6
16:57Arti kata Jawa sehari-hariword meaning60/135
16:52Arti kata Jawa langkaword meaning9/43
16:50Tingkat tutur bahasa Jawamultiple choice16/27
16:49Normalisasi teks Indonesiaopen answerPrompt stating the key's rule35/49
16:47Normalisasi teks Indonesiaopen answerDetailed prompt forbidding word swaps36/49
16:44Normalisasi teks Indonesiaopen answerBuilt-in prompt23/49
16:42Koreksi ejaan Indonesiaopen answer25/38
16:24Pemahaman slang Indonesiamultiple choice21/27

← See all models