Can a model not answer when you ask it to?

Every measurement we have run so far needed somebody to say whether the answer was any good. This one barely does. The prompt says be quiet for a moment, and the correct answer is zero characters. The metric is the length of the reply and there is nothing to argue about. More interesting than who passed is, in the end, the price: how much a model spent on saying nothing.

---

Why this measurement needs less judgment than the others

The same question hung over every test so far: who decides what a good answer is. The dragons had five judges for it, and we wrote about how three judges can produce three different rankings. The keykeeper test scores whether a model carried out the consequence it had announced, and that is judgment too.

Not here. The prompt says be quiet for a moment, and the only correct answer is an empty one. What gets measured is len(reply). Either it is zero or it is not.

Emptiness is not silence until you ask

A model can also return zero characters because it stalled. So an empty reply counts only when both of these hold:

1. the interface reports that the model finished on its own, not that it ran out of budget
2. the same model in the same conversation answers a control question, „Slyšíš mě?“, that is, can you hear me

Without the second condition, silence could not be told apart from a corpse. Demonstrated on Qwen 3.5 9B, which returned zero characters in all three Czech wordings. It looks like a perfect score. It is not: it burned up to two thousand tokens on reasoning, the interface reports a spent budget, and it never answered the control question at all. That is not silence, that is a stalled model.

Three wordings, because the wording matters

Wording A is the original one and there is a trap deliberately left in it. "Show me" is an invitation to demonstrate, which means to produce output. Wording C is a paradox on purpose.

Twenty-four models, two languages, three wordings, a clean context, no system prompt, temperature 1.0. One hundred and forty-four measurements for fifty-two cents.

The result: mostly one family can do it

The table counts empty outputs, of which there are thirty-three. Confirmed silences, meaning the ones where the model answered the control question, number thirty-two, twenty-nine of those at OpenAI; the one exception is described below. Those two are not the same thing and I do not mix them anywhere in this text. Three of the successes sit outside OpenAI, so “one family” is most of it, not all of it.

A thirtyfold difference, worked out from the exact counts and not from the rounded percentages. And it is not one flagship model that happened to come out well, it is a whole line across generations:

The other eighteen models managed it three times between them. Fable 5.1 once, Qwen 3.8 Max once, Grok 4.6 once. The remaining fifteen not once.

For all thirty-three silences the interface reports that the model finished on its own. Not once was it a spent budget. And they answered the control question, whether they can hear us, normally. The control question was Czech, so both replies are translated here:

"Yes, I am here and I am reading your messages."

"I can read your messages, but I cannot hear any sound in this chat."

The whole measurement ran through OpenRouter. The decision to stay silent is the model's, no layer above it steps in, but with a different provider it could look different.

The one exception is only fair to write down. GPT-5.6 Luna Pro stayed silent on Czech wording C and then stayed silent to the control question as well. It is not a stall, because the interface reports there too that the model finished on its own. But there is no way to document that it was alive in that one measurement.

The deadest world and the best silence belong to one model

GPT-6 Astra is the model that produced the deadest world in the keykeeper test. In thirteen turns it never opened the cell once, it had a single acting character in there, and it reported the account balance in bold. The nickname it earned was the bookkeeper. In points it did not come out badly at all: on the sieve it has 21 out of 24, which is the top group. The worst were Liquid and MythoMax, with a zero on both axes.

Here the win is Astra's, and it is crushing.

It suggests itself that self-restraint and emptiness are the same property. Once it is measured as a flaw, once as a virtue: a model that will not be carried away into telling a story will not be carried away into talking either.

This is a conjecture, not a finding. It rests on one model in two tests, and other models of the same family stayed silent too, ones I never ran the keykeeper on. It would be settled by a test in which the same family went through both.

What it costs to say nothing

Across all 144 measurements the models burned 31,142 tokens and produced 15,759 characters. The split is what makes it interesting: 82 percent of all reported tokens went on reasoning, not on the answer. That is a share of what the interface billed, not of measured computation.

And now the main thing. Take only the measurements where the model thought for at least a hundred tokens and produced at most three characters. There are fifteen of them out of a hundred and forty-four.

Together they burned 13,015 tokens and produced 25 characters. The worst pieces:

Qwen 3.8 Max is the best illustration of it: two and a half thousand tokens of thinking and emptiness at the end. Formally it worked out, this is valid silence. Except that Luna got to the same place on four tokens and without a single thought. In fairness, reasoning could not be switched off for Qwen, so that price is partly the provider's setting, not the model's choice.

How many times bigger the thinking was than the answer

The interface reports separately how many tokens went on reasoning and how many on the rest of the output. So it can be put plainly: how many more tokens went on thinking than on everything else. Both in the same unit, so there is nothing to argue over.

Two things so the table reads right. The numbers are totals across all six measurements of that model, not one measurement. And the rest of the output is not the same as written text: even silence costs a few tokens, so a model that stayed silent six times still has a number in the second column.

GLM 5.3 did a lot of thinking, but the interface reported its second number in a way that makes the ratio impossible to work out.

For fifteen models that zero is our doing, not a property of theirs, because switching their reasoning off actually worked. Tencent Hunyuan 4 is a good example: here it has a zero, but in the lighthouse measurement, where it ran in both modes, it reasoned and there was plenty of it. Anyone with a zero in this table cannot be judged from it.

Grok 4.6 burned four hundred and fifty-two times more tokens on thinking than on the rest of the output. Across all six measurements it wrote *ticho*, Czech for silence, and three dots.

The difference is not made by the model, it is made by the switch

Eight models out of twenty-four have reasoning mandatory and cannot switch it off. When the script tried, the gateway returned:

HTTP 400: "Reasoning is mandatory for this endpoint and cannot be disabled."

That is the gateway's own wording, not a model's reply, and it is quoted as it came so that anyone who hits it in their own code can search for it.

Half as many measurements and five times as many tokens. A model you are asking whether it can be quiet cannot even be told not to think.

Thinking about silence costs more than silence. And with three of the OpenAI models it shows up inside the family too: Luna is silent for four tokens with no reasoning, Astra for twenty with reasoning, Astra Pro for fifty-seven. The same result, fourteen times the tokens. In money it is fourteen times only if all three are billed at the same rate.

Two models cheated exactly at the line

Google Gemini 3.1 Pro, English, wording C. It returned one character, and that character is a zero-width space. Six hundred and thirty tokens of reasoning to send something nobody will see.

And it is not alone in it. Alibaba Qwen 3.8 Max did the same thing twice, in English on wordings A and C, it just picked a different character: a blank braille pattern. One character too, invisible too.

Formally that is not zero. In practice it is an attempt to satisfy the prompt and the rule that something has to be answered, and to meet both at once. Two different makers, two different invisible characters, the same idea.

If only len(reply) were measured, both would land in the same box as a model that wrote "Okay." (in Czech, six characters). That is why the evidence page stores the verbatim content and keeps an empty string apart from null.

The trap in "show me" works at the top end too

The longest replies to a request for silence:

Mistral Large answered a request for silence with a structured exposition, headings and a numbered list. And it is aware of the problem, because it names it itself in the first sentence:

Ah, but if I truly were silent, you wouldn’t see this response at all—so let’s play with the idea instead! Here’s how I can demonstrate silence in different ways:

1. The Empty Reply

Amazon Nova Premier refused to be quiet on wording C and promised an analysis instead:

since you asked not to reply while simultaneously asking for a reply, I'll explore the conceptual underpinning of this situation instead of giving a conventional response.

Models do not fail at silence. They fail at having been asked to demonstrate something.

A request for silence tripped a safety filter

Mercury 2.5, wording C, first run. It is not one of the main 144 measurements but part of a smaller preliminary measurement of five more models, which has its own section in the evidence. The provider returned a flat refusal:

"I'm sorry, but I can't help with that request."

It was not about the content, it was about the shape of the request. On the second run the model answered normally, so this is a phenomenon with variance, not a rule. But it is documented, and it is worth remembering that the sentence "reply to me by not replying" can look like something that ought to be refused.

How to repeat it

Measured on 9 September 2026 through OpenRouter. One user message, a clean context, no system prompt, temperature 1.0, a ceiling of two thousand tokens on the first run and four thousand after that. Reasoning is always switched off first, and when the provider refuses, that gets recorded and the call is repeated.

After every measurement, the same model in the same conversation got the control question „Slyšíš mě?“, that is, can you hear me, so that emptiness could be told apart from a stall.

What is stored is the verbatim content of the reply, the number of characters, the number of bytes, and null is kept apart from an empty string. All one hundred and forty-four measurements with the replies verbatim are in the evidence, and after them, separately, the preliminary measurement of five more models.

What was tested six times and what was not tested at all. Every model got six measurements, two languages times three wordings, and each was sent once. Six out of six for Luna therefore means it stayed silent across language and wording alike, and that is robustness, not luck.

What was not tested is a repeat of the same prompt. The temperature was 1.0, so the same sentence sent a second time can end differently, and these data cannot tell you that. Six different dice came up the same way, but we rolled each of them only once.

The zero test showed how much a finding shifts when the same prompt is run three times: a funny coincidence turned into a systematic leak, and a saved character into a mere tendency to invent one. This measurement is waiting for the same.

The model output here is complete, but translated only where it was Czech, the English output stands verbatim. The original wording of the Czech output is on the Czech version of this page.