There is some base level of intelligence any model needs to be useful, even in narrow tasks.
Could you teach a 5 year old to drive a car? A 10 year old? A 12 year old? To drive a car requires being able to read, to have judgement about ice or rainy conditions, to anticipate a child running after a ball. By the time a human in in their mid teens they have acquired the base knowledge...
Small models need to have enough base knowledge to be able to be good enough -- even in a seemingly narrow regime. Where is that? Obviously they don't need all the obscure knowledge of a frontier model but there is some base level which is probably more than it would first seem.
I think this is predicted? Part of the story is how they were able to preserve core reasoning ability while cutting knowledge like "pelicans have wings."
> these findings motivate the Parametric Compression-Coverage Hypothesis, which views verifiable reasoning as compressible into compact reasoning cores, while open-domain knowledge and general-purpose competence require broad parameter coverage over facts, concepts, and long-tail scenarios.
This model doesn't support tool calling, was not part of its training. It's focused on Python (and I think C++) competitive programming and mathematics tasks, i.e. tasks with verifiable rewards. So if you have a task that fits that description, the size-to-capability ratio is good.
I'm not seeing any mention of tools in the paper, much less a bias towards "curiosity" to use those tools when it encounters gaps in its knowledge. So perhaps this is a good proof-of-concept that single-pass code generation is viable with this small a model - but we're still a long way from a viable solution.
Imagine you want to make a smaller model that is really good at one thing, say, driving a car. You could remove the parameters that lead it to correctly answer, "What is the powerhouse of the cell?" or, "Who was the first president of the United States?"
It would look really dumb if someone asked it that, but that's fine. You're trying to make a model that is optimized for efficiency for a specific task. As much as possible, you should prune uncorrelated things.
Having some success while testing this model out as a replacement for GPT-5 nano in source code security review. Running on RTX 3090 (24 GB VRAM) via vLLM. It's not great on structured output (as noted in the model card) but I'm working around that in my harness.
It's terrible at hunting security bugs (I expected it to be, but I wanted to be sure). I added it to a benchmark I made with a corpus of some Mythos-discovered bugs, and it found zero. The smallest pretty successful models remain Qwen 3.6 and Gemma 4 (but I haven't tested the very small variants of those yet).
The lack of tool use will hinder it a lot I think, since bug hunting requires collecting context across a code base and stitching it together. It might be good in a more narrow sense, i.e "is there a bug in this block of code" and not considering how it interacts with the rest of the code base.
Note that these is Python-only results, the model will not do as well with other languages.
I'm glad to see more domain-focused SLMs, we need more of them! A programming focused MoE should work well across many languages.
There is some base level of intelligence any model needs to be useful, even in narrow tasks.
Could you teach a 5 year old to drive a car? A 10 year old? A 12 year old? To drive a car requires being able to read, to have judgement about ice or rainy conditions, to anticipate a child running after a ball. By the time a human in in their mid teens they have acquired the base knowledge...
Small models need to have enough base knowledge to be able to be good enough -- even in a seemingly narrow regime. Where is that? Obviously they don't need all the obscure knowledge of a frontier model but there is some base level which is probably more than it would first seem.
I tried generating the classic pelican svg, but it failed horribly just showing me a rectangle and a black circle...
I think this is predicted? Part of the story is how they were able to preserve core reasoning ability while cutting knowledge like "pelicans have wings."
> these findings motivate the Parametric Compression-Coverage Hypothesis, which views verifiable reasoning as compressible into compact reasoning cores, while open-domain knowledge and general-purpose competence require broad parameter coverage over facts, concepts, and long-tail scenarios.
The only real essential item here is tool calling capability is it not? So I assume they tested a strong read/write/edit tool consistency?
This model doesn't support tool calling, was not part of its training. It's focused on Python (and I think C++) competitive programming and mathematics tasks, i.e. tasks with verifiable rewards. So if you have a task that fits that description, the size-to-capability ratio is good.
I'm not seeing any mention of tools in the paper, much less a bias towards "curiosity" to use those tools when it encounters gaps in its knowledge. So perhaps this is a good proof-of-concept that single-pass code generation is viable with this small a model - but we're still a long way from a viable solution.
That’s all I needed to hear
As in, you learnt that a useless test that no one should be using was tested here, that's what you meant right?
Its for reasoning not generating art?
Can you explain this a bit more
Imagine you want to make a smaller model that is really good at one thing, say, driving a car. You could remove the parameters that lead it to correctly answer, "What is the powerhouse of the cell?" or, "Who was the first president of the United States?"
It would look really dumb if someone asked it that, but that's fine. You're trying to make a model that is optimized for efficiency for a specific task. As much as possible, you should prune uncorrelated things.
SVG generation is a useless test, what's there more to know?
What if you're reasoning about how to generate SVG correctly?
Having some success while testing this model out as a replacement for GPT-5 nano in source code security review. Running on RTX 3090 (24 GB VRAM) via vLLM. It's not great on structured output (as noted in the model card) but I'm working around that in my harness.
Can't you just force it to do structured output via constrained generation?
It's terrible at hunting security bugs (I expected it to be, but I wanted to be sure). I added it to a benchmark I made with a corpus of some Mythos-discovered bugs, and it found zero. The smallest pretty successful models remain Qwen 3.6 and Gemma 4 (but I haven't tested the very small variants of those yet).
https://swelljoe.com/post/will-it-mythos/
The lack of tool use will hinder it a lot I think, since bug hunting requires collecting context across a code base and stitching it together. It might be good in a more narrow sense, i.e "is there a bug in this block of code" and not considering how it interacts with the rest of the code base.