> "In particular, Qwen3.5-Plus is the hosted version corresponding to Qwen3.5-397B-A17B with more production features, e.g., 1M context length by default, official built-in tools, and adaptive tool use."
Anyone knows more about this? The OSS version seems to have has 262144 context len, I guess for the 1M they'll ask u to use yarn?
Does anyone know what kind of RL environments they are talking about? They mention they used 15k environments. I can think of a couple hundred maybe that make sense to me, but what is filling that large number?
Last Chinese new year we would not have predicted a Sonnet 4.5 level model that runs local and fast on a 2026 M5 Max MacBook Pro, but it's now a real possibility.
Wow, the Qwen team is pushing out content (models + research + blogpost) at an incredible rate! Looks like omni-modals is their focus? The benchmark look intriguing but I can’t stop thinking of the hn comments about Qwen being known for benchmaxing.
Sad to not see smaller distills of this model being released alongside the flaggship. That has historically been why i liked qwen releases. (Lots of diffrent sizes to pick from from day one)
The thing I would appreciate much more than performance in "embarrassing LLM questions" is a method of finding these, and figuring out by some form of statistical sampling, what the cardinality is of those for each LLM.
It's difficult to do because LLMs immediately consume all available corpus, so there is no telling if the algorithm improved, or if it just wrote one more post-it note and stuck it on its monitor. This is an agency vs replay problem.
Preventing replay attacks in data processing is simple: encrypt, use a one time pad, similarly to TLS. How can one make problems which are at the same time natural-language, but where at the same time the contents, still explained in plain English, are "encrypted" such that every time an LLM reads them, they are novel to the LLM?
Perhaps a generative language model could help. Not a large language model, but something that understands grammar enough to create problems that LLMs will be able to solve - and where the actual encoding of the puzzle is generative, kind of like a random string of balanced left and right parentheses can be used to encode a computer program.
Maybe it would make sense to use a program generator that generates a random program in a simple, sandboxed language - say, I don't know, LUA - and then translates that to plain English for the LLM, and asks it what the outcome should be, and then compares it with the LUA program, which can be quickly executed for comparison.
Either way we are dealing with an "information war" scenario, which reminds me of the relevant passages in Neal Stephenson's The Diamond Age about faking statistical distributions by moving units to weird locations in Africa. Maybe there's something there.
I'm sure I'm missing something here, so please let me know if so.
I like your idea of finding the pattern of those "embarrassing LLM questions". However, I do not understand your example. What is a random program? Is it a program that compiles/executes without error but can literally do anything? Also, how do you translate a program to plain English?
A randomly generated program from a space of programs defined by a set of generating actions.
A simple example is a programming language that can only operate on integers, do addition, subtraction, multiplication, and can check for equality. You can create an infinite amount of programs of this sort. Once generated, these programs are quickly evaluated within a split second. You can translate them all to English programmatically, ensuring grammatical and semantical correctness, by use of a generating rule set that translates the program to English. The LLM can provide its own evaluation of the output.
For example:
program:
1 + 2 * 3 == 7
evaluates to true in its machine-readable, non-LLM form.
LLM-readable english form:
Is one plus two times three equal to seven?
The LLM will evaluate this to either true or false. You compare with what classical execution provided.
Now take this principle, and create a much more complex system which can create more advanced interactions. You could talk about geometry, colors, logical sequences in stories, etc.
for Google AI Overview (not sure which Gemini model is used for it, must be something smaller than regular model), looks like search/RAG helps it get it right - since it relies on LinkedIn and Hacker News (!) posts to respond correctly...
as of Feb 16, 2026:
====
Drive the car. While 50 meters is a very short distance, the car must be present at the car wash to be cleaned, according to LinkedIn users [1]. Walking would leave your car at home, defeating the purpose of the trip, notes another user.
Why Drive: The car needs to be at the location to be cleaned. It's only a few seconds away, and you can simply drive it there and back, says a Hacker News user. [2]
Why Not to Walk: Walking there means the car stays home, as noted in a post. [3]
The best option is to start the engine, drive the 50 meters, and let the car get washed.
But the regular Gemini reasons correctly by itself, without any references:
====
Unless you have a very long hose and a very patient neighbor, you should definitely drive.
Washing a car usually requires, well, the car to be at the wash. Walking 50 meters—about half a New York City block—is great for your step count, but it won't get your vehicle any cleaner!
Are you headed to a self-service bay or an automatic tunnel wash?
The fact that it quotes discussions about LLM failures kinda counts as cheating. That just means you need to burn a fresh question to get a real idea of its reasoning.
Would love to see a Qwen 3.5 release in the range of 80-110B which would be perfect for 128GB devices. While Qwen3-Next is 80b, it unfortunately doesn't have a vision encoder.
Is it just me or are the 'open source' models increasingly impractical to run on anything other than massive cloud infra at which point you may as well go with the frontier models from Google, Anthropic, OpenAI etc.?
It's because their target audience are enterprise customers who want to use their cloud hosted models, not local AI enthusiasts. Making the model larger is an easy way to scale intelligence.
Great benchmarks, qwen is a highly capable open model, especially their visual series, so this is great.
Interesting rabbit hole for me - its AI report mentions Fennec (Sonnet 5) releasing Feb 4 -- I was like "No, I don't think so", then I did a lot of googling and learned that this is a common misperception amongst AI-driven news tools. Looks like there was a leak, rumors, a planned(?) launch date, and .. it all adds up to a confident launch summary.
What's interesting about this is I'd missed all the rumors, so we had a sort of useful hallucination. Notable.
Does anyone else have trouble loading from the qwen blogs? I always get their placeholders for loading and nothing ever comes in. I don’t know if this is ad blocker related or what… (I’ve even disabled it but it still won’t load)
at this point it seems every new model scores within a few points of each other on SWE-bench. the actual differentiator is how well it handles multi-step tool use without losing the plot halfway through and how well it works with an existing stack
I just started creating my own benchmarks (very simple questions for humans but tricky for AI, like how many r's in strawberry kind of questions, still WIP).
44 comments
[ 2.0 ms ] story [ 66.7 ms ] thread> "In particular, Qwen3.5-Plus is the hosted version corresponding to Qwen3.5-397B-A17B with more production features, e.g., 1M context length by default, official built-in tools, and adaptive tool use."
Anyone knows more about this? The OSS version seems to have has 262144 context len, I guess for the 1M they'll ask u to use yarn?
[1] https://huggingface.co/Qwen/Qwen3.5-397B-A17B
I've long thought multi-modal LLMs should be strong enough to do RL for TikZ and SVG generation. Maybe Google is doing it.
It's difficult to do because LLMs immediately consume all available corpus, so there is no telling if the algorithm improved, or if it just wrote one more post-it note and stuck it on its monitor. This is an agency vs replay problem.
Preventing replay attacks in data processing is simple: encrypt, use a one time pad, similarly to TLS. How can one make problems which are at the same time natural-language, but where at the same time the contents, still explained in plain English, are "encrypted" such that every time an LLM reads them, they are novel to the LLM?
Perhaps a generative language model could help. Not a large language model, but something that understands grammar enough to create problems that LLMs will be able to solve - and where the actual encoding of the puzzle is generative, kind of like a random string of balanced left and right parentheses can be used to encode a computer program.
Maybe it would make sense to use a program generator that generates a random program in a simple, sandboxed language - say, I don't know, LUA - and then translates that to plain English for the LLM, and asks it what the outcome should be, and then compares it with the LUA program, which can be quickly executed for comparison.
Either way we are dealing with an "information war" scenario, which reminds me of the relevant passages in Neal Stephenson's The Diamond Age about faking statistical distributions by moving units to weird locations in Africa. Maybe there's something there.
I'm sure I'm missing something here, so please let me know if so.
A simple example is a programming language that can only operate on integers, do addition, subtraction, multiplication, and can check for equality. You can create an infinite amount of programs of this sort. Once generated, these programs are quickly evaluated within a split second. You can translate them all to English programmatically, ensuring grammatical and semantical correctness, by use of a generating rule set that translates the program to English. The LLM can provide its own evaluation of the output.
For example:
program:
1 + 2 * 3 == 7
evaluates to true in its machine-readable, non-LLM form.
LLM-readable english form:
Is one plus two times three equal to seven?
The LLM will evaluate this to either true or false. You compare with what classical execution provided.
Now take this principle, and create a much more complex system which can create more advanced interactions. You could talk about geometry, colors, logical sequences in stories, etc.
as of Feb 16, 2026:
====
Drive the car. While 50 meters is a very short distance, the car must be present at the car wash to be cleaned, according to LinkedIn users [1]. Walking would leave your car at home, defeating the purpose of the trip, notes another user.
Why Drive: The car needs to be at the location to be cleaned. It's only a few seconds away, and you can simply drive it there and back, says a Hacker News user. [2]
Why Not to Walk: Walking there means the car stays home, as noted in a post. [3]
The best option is to start the engine, drive the 50 meters, and let the car get washed.
[1] https://www.linkedin.com/posts/ramar_i-saw-this-llm-failure-... [2] https://news.ycombinator.com/item?id=47034546 [3] https://x.com/anirudhamudan/status/2022152959073956050/photo...
But the regular Gemini reasons correctly by itself, without any references:
==== Unless you have a very long hose and a very patient neighbor, you should definitely drive. Washing a car usually requires, well, the car to be at the wash. Walking 50 meters—about half a New York City block—is great for your step count, but it won't get your vehicle any cleaner! Are you headed to a self-service bay or an automatic tunnel wash?
Interesting rabbit hole for me - its AI report mentions Fennec (Sonnet 5) releasing Feb 4 -- I was like "No, I don't think so", then I did a lot of googling and learned that this is a common misperception amongst AI-driven news tools. Looks like there was a leak, rumors, a planned(?) launch date, and .. it all adds up to a confident launch summary.
What's interesting about this is I'd missed all the rumors, so we had a sort of useful hallucination. Notable.
https://openrouter.ai/qwen/qwen3.5-plus-02-15
Qwen3.5 is doing ok on my limited tests: https://aibenchy.com
[1]: https://github.com/QwenLM/Qwen3-TTS