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 Indonesia39/42 92.9%
Tingkat tutur bahasa Jawa25/27 92.6%
Arti kata Jawa sehari-hari107/135 79.3%
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.37/49 75.5%
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.35/49 71.4%
Koreksi ejaan Indonesia23/38 60.5%
Arti kata Jawa langka22/43 51.2%
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.24/49 49.0%
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 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.71.4%$0.000095
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.75.5%$0.000096
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.49.0%$0.000116
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.
63,480 in, 102,703 out
inputoutput
Pemahaman slang Indonesia10,888 · 4,981
Tingkat tutur bahasa Jawa4,960 · 6,495
Arti kata Jawa sehari-hari6,313 · 36,231
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.10,240 · 14,955
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.10,998 · 14,585
Koreksi ejaan Indonesia11,085 · 13,176
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.8,996 · 12,280
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.3.64 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.4.09 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.4.53 s
Arti kata Jawa langka4.67 s
Koreksi ejaan Indonesia5.02 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 Indonesia25/27 92.6%
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.110/135 81.5%
Log12 calls to this model, spread across 4 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
- 23:04Pemahaman slang Indonesiamultiple choice39/42
1 runs
- 21:32Arti kata Jawa sehari-hariword meaning107/135
8 runs
- -Keteranganestimated dateArti kata Jawa langkaword meaning22/43
- -Keteranganestimated dateArti kata Jawa sehari-hariword meaning110/135
- 08:17Normalisasi teks Indonesiaopen answerPrompt stating the key's rule37/49
- 08:16Normalisasi teks Indonesiaopen answerDetailed prompt forbidding word swaps35/49
- 08:12Normalisasi teks Indonesiaopen answerBuilt-in prompt24/49
- 06:46Tingkat tutur bahasa Jawamultiple choice25/27
- 03:09Koreksi ejaan Indonesiaopen answer23/38
- 03:08Pemahaman slang Indonesiamultiple choice25/27
2 runs
- 01:04Arti kata Jawa sehari-hariword meaning110/135
- 00:59Arti kata Jawa sehari-hariword meaning110/135