Ox Alpha
stealth · released Aug 20, 2026
- Type
- Closed
- Input
- None held
- Output
- None held
- Cached
- None held
We don't hold a list price for this model yet · hosted only — we have no record of published weights
Our take
Written Sep 23, 2026Ox Alpha is a model we list no download for, and no host either, so there is no route we can point you to. Its only measured quality is a set of LiveBench results from June 2026 that place it in the bottom half of the field on every board we hold.
Consider it only if you can already reach it through a host of your own, since we list none. Its strongest measured area is competition and olympiad mathematics, and it reads tables and event sequences better than prose. Skip it if you need measured language comprehension or mathematics, where it places 49th of 51, or if you need fixes landed in an existing codebase without review.
The case for it
- Its strongest measured area is competition and olympiad mathematics, at 77.53% on LiveBench Mathematics — set-piece questions rather than the arithmetic inside a working project.
- It reads tables and event sequences well, at 75.77% on LiveBench Data Analysis, so structured data is a better fit than prose.
- Pictures and clips go in with the question, so a screenshot or a clip does not have to be described in words first.
The case against it
- We list no download for it and no hosted offer, so using it means finding a host yourself, and no licence is supplied to tell you what you may do with it.
- Bottom of the field on language and mathematics: 49th of 51 on LiveBench Language via Max as of 25 Jun 2026, and 49th of 51 on LiveBench Mathematics via Max as of 25 Jun 2026.
- Agentic coding is its weakest measured result, at 52.63% inside an agent harness — the lowest of its eight LiveBench figures.
How good is it?
EverydayGeneral questions and everyday reasoning
Not yet scored on Arena Text (overall). It is on LiveBench Data Analysis, in 27th of 58 with 75.77.
CodingWriting and fixing code on its own
Not yet scored on Arena Coding. It is on LiveBench Coding, in 39th of 58 with 75.75.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on LiveBench Agentic Coding, in 31st of 58 with 52.63.
WritingDrafting and rewriting prose
Not yet scored on Arena Creative Writing. It is on LiveBench Language, in 56th of 58 with 66.14.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model8 scoresEvery figure we hold, from 8 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to get it
We hold no priced listing for Ox Alpha.
There is no copy to download and no host in our price data, so stealth is where to look. We watch OpenRouter, the provider APIs we track and the LiteLLM price set; this version appears in none of them, which is a gap in what we collect rather than a statement about what stealth sells.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- We don't hold a list price for this model yet — the gap is ours, not the lab's.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images and video in, text out
- Catalogue slug
- stealth-ox-alpha