Quick summary
Results
How many questions each model answered correctly, from the exact same set. The bars show the count of correct answers, not a general ranking of model ability.
The model is asked to explain what a single word means in free text. An answer counts as correct if it contains every word of one of our approved keys.
A model whose name does not end in a date is called through an id that does not pin the version. The provider may swap the model behind that id at any time without notice, so the figures apply to whichever version was active when the run happened.
How these figures are computed
arti-kata-v1KeteranganHow word-meaning questions are asked. The model is asked to explain what a single word means, with no options offered, so the answer is free text.scoring kunci-alias-v1KeteranganHow word-meaning answers are scored. An answer counts as correct if it contains every word of one of our approved keys, compared on word stems. Affixes, word order, and extra surrounding text do not disqualify it.question version 6dfcc448bbd5KeteranganA 12-character fingerprint of every question the model saw: item number, question text, answer options, and option order. Changing a single word changes the fingerprint. Scores under different fingerprints answer different questions, so this page only joins figures that share one.answer key version 0a1bc07f67bcKeteranganA 12-character fingerprint of the answer key: the reference, the other answers we accept, and speaker verdicts for items no machine may score. The questions can stay identical while the key changes, and when that happens scores move without a single word of the question changing. That is why it is kept apart from the question version.Per-model detail
The same figures as the chart above, plus the cost per correct answer, the wait time, and the date of the last run. Any column that cannot be guessed from its name carries its own explanation.
| Model | CorrectKeteranganHow many answers matched the key, out of the items scored. | $/correctKeteranganThe cost of one full run divided by ALL its correct answers, including those in the Held back column. The Correct column shows the public slice only, so the denominator here is the sum of both columns. NOT the cost per call: a cheap model that gets a lot wrong can cost more per correct answer than a model that costs more per call. | LatencyKeteranganMedian wait for a single call. Median rather than mean, so one stalled call does not move the number. | Last runKeteranganThe last date we ran this model on the same questions and answer key. |
|---|---|---|---|---|
| Gemini 3.5 FlashGoogle | 40/4393.0% | $0.003175$0.1270 | 3,418 msmedian | Keteranganestimated date |
| GPT-5.6 LunaOpenAI | 35/4381.4% | $0.000113$0.0040 | 3,708 msmedian | Keteranganestimated date |
| Gemma 4 31BGoogle | 26/4360.5% | $0.000019$0.0005 | 1,913 msmedian | |
| DeepSeek V4 Flash 0731DeepSeek | 22/4351.2% | $0.000114$0.0025 | 4,670 msmedian | Keteranganestimated date |
| Gemma-SEA-LION v4.5 E2B-ITlocal | 9/4320.9% | - | 843 msmedian | |
| Llama3 8B CPT Sahabat-AI v1 Instructlocal | 4/439.3% | - | 567 msmedian | |
| Solar Pro 4Upstage | 4/439.3% | $0.000057$0.0002 | 6,807 msmedian | |
| Nemotron 3.5 LightningNVIDIA | 3/437.0% | $0.003700$0.0111 | 3,669 msmedian | |
| Llama 3.1 8B Instructlocal | 1/432.3% | - | 543 msmedian | |
| Mistral Small 3Mistral | 1/432.3% | $0.000475$0.0005 | 1,403 msmedian | Keteranganestimated date |
Models marked local run on our own hardware, so there is no bill to record and the wait time measures our machine, not a service anyone else can buy. The score is still comparable: the items, the key, and the temperature are identical to every other row here.
Every figure in this table can be recomputed from the raw data. Open the data →
Cost and tokensCheapest per correct answer: Gemma 4 31B ($0.000019). Most expensive: Nemotron 3.5 Lightning ($0.003700).Show chartsHide
All cost figures are in US dollars.
Cost per correct answer
The model with the highest score is not always the cheapest one. This divides the cost of one full test by its number of correct answers.
Cost of one full run
The raw figure, before dividing by the number of correct answers. Every model answered the exact same questions, so this is directly comparable: it is what you pay to run this benchmark once on each model.
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 almost all of the cost difference between models comes from. A model with no bar has no token record, which is not the same as zero.
6 models are not drawn here because their token counts were never recorded. Those runs come from an older path whose ledger did not store them, and drawing them as zero would read as models that used no tokens at all.