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.
8 benchmarks
Pemahaman slang Indonesia42/42 100.0%
Tingkat tutur bahasa Jawa23/27 85.2%
Normalisasi teks Indonesiaquestion version 3KeteranganWe asked this benchmark with several different phrasings of the question, on the same items and the same answer key. Scores across phrasings are not directly comparable; open the benchmark page to see them side by side.41/49 83.7%
Arti kata Jawa sehari-hari112/135 83.0%
Arti kata Jawa langka35/43 81.4%
Normalisasi teks Indonesiaquestion version 2KeteranganWe asked this benchmark with several different phrasings of the question, on the same items and the same answer key. Scores across phrasings are not directly comparable; open the benchmark page to see them side by side.38/49 77.6%
Koreksi ejaan Indonesia25/38 65.8%
Normalisasi teks Indonesiaquestion version 1KeteranganWe asked this benchmark with several different phrasings of the question, on the same items and the same answer key. Scores across phrasings are not directly comparable; open the benchmark page to see them side by side.22/49 44.9%
How far the cost pays off
Sorted by the cheapest correct answer first. The left column shows how many items were answered correctly, so a top row with a long left bar means both cheap and accurate.
8 with cost on record
Correct answersCost per correct answer
Normalisasi teks Indonesiaquestion version 1KeteranganWe asked this benchmark with several different phrasings of the question, on the same items and the same answer key. Scores across phrasings are not directly comparable; open the benchmark page to see them side by side.44.9%$0.000069
Normalisasi teks Indonesiaquestion version 3KeteranganWe asked this benchmark with several different phrasings of the question, on the same items and the same answer key. Scores across phrasings are not directly comparable; open the benchmark page to see them side by side.83.7%$0.000074
Normalisasi teks Indonesiaquestion version 2KeteranganWe asked this benchmark with several different phrasings of the question, on the same items and the same answer key. Scores across phrasings are not directly comparable; open the benchmark page to see them side by side.77.6%$0.000081
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.
61,262 in, 33,725 out
inputoutput
Pemahaman slang Indonesia10,310 · 831
Tingkat tutur bahasa Jawa4,754 · 528
Normalisasi teks Indonesiaquestion version 3KeteranganWe asked this benchmark with several different phrasings of the question, on the same items and the same answer key. Scores across phrasings are not directly comparable; open the benchmark page to see them side by side.9,999 · 5,122
Arti kata Jawa sehari-hari6,029 · 12,966
Normalisasi teks Indonesiaquestion version 2KeteranganWe asked this benchmark with several different phrasings of the question, on the same items and the same answer key. Scores across phrasings are not directly comparable; open the benchmark page to see them side by side.10,689 · 5,256
Koreksi ejaan Indonesia10,655 · 6,923
Normalisasi teks Indonesiaquestion version 1KeteranganWe asked this benchmark with several different phrasings of the question, on the same items and the same answer key. Scores across phrasings are not directly comparable; open the benchmark page to see them side by side.8,826 · 2,099
1 benchmarks are not drawn here: those runs came from an older path whose ledger did not store token counts. Not recorded, not zero.
Wait time per call
Median wait for a single call on each benchmark. Median rather than mean, so one stalled call does not move the number.
8 with wait time on record
Normalisasi teks Indonesiaquestion version 1KeteranganWe asked this benchmark with several different phrasings of the question, on the same items and the same answer key. Scores across phrasings are not directly comparable; open the benchmark page to see them side by side.1.03 s
Normalisasi teks Indonesiaquestion version 3KeteranganWe asked this benchmark with several different phrasings of the question, on the same items and the same answer key. Scores across phrasings are not directly comparable; open the benchmark page to see them side by side.2.02 s
Normalisasi teks Indonesiaquestion version 2KeteranganWe asked this benchmark with several different phrasings of the question, on the same items and the same answer key. Scores across phrasings are not directly comparable; open the benchmark page to see them side by side.2.20 s
Koreksi ejaan Indonesia2.70 s
Arti kata Jawa langka3.71 s
Test coverage
6/ 6
This model has been tested on all 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 rowsclose
Pemahaman slang Indonesia27/27 100.0%
Arti kata Jawa sehari-hari3 runsKeteranganThis benchmark was run 3 times on this version of the items or key, and the bar draws the midpoint of those 3 results.121/135 87.8%
Log12 calls to this model, spread across 5 days.OpenClose
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.
1 runs
- 22:49Pemahaman slang Indonesiamultiple choice42/42
1 runs
- 20:50Arti kata Jawa sehari-hariword meaning112/135
8 runs
- -Keteranganestimated dateArti kata Jawa langkaword meaning35/43
- -Keteranganestimated dateArti kata Jawa sehari-hariword meaning116/135
- 07:47Normalisasi teks Indonesiaopen answerPrompt stating the key's rule41/49
- 07:16Normalisasi teks Indonesiaopen answerBuilt-in prompt22/49
- 07:00Normalisasi teks Indonesiaopen answerDetailed prompt forbidding word swaps38/49
- 06:54Pemahaman slang Indonesiamultiple choice27/27
- 06:50Koreksi ejaan Indonesiaopen answer25/38
- 06:34Tingkat tutur bahasa Jawamultiple choice23/27
1 runs
- 00:00Arti kata Jawa sehari-hariword meaning119/135
1 runs
- 22:46Arti kata Jawa sehari-hariword meaning121/135