Cloudflare Tries to Outplay Jev With Open-Weight Clef Models (theregister.com) 15
Cloudflare has launched two open-weight decision models, Clef and Clef-flash, designed for structured yes/no, multiple-choice, and ranking tasks while also supporting images, video, and up to a 64K context window. Cloudflare says its models outperform TypeSafe's Jev on several benchmarks and can run locally from Hugging Face. The Register reports: For starters, Clef has an LLM backbone. According to Cloudflare, Clef uses specially post-trained, frozen versions of Qwen3.8-27B and Qwen3.5-9B for Clef and Clef-flash, respectively, with the Qwen backbone performing a prefill-only pass during inference. Clef is still fast - faster than Jev, to be fair - and scores choices in parallel after that prefill-only pass. It's not clear what Jev's underlying architecture is, as TypeSafe has kept that a secret.
As for its speed and capability, Clef moves fast. Cloudflare ran it against Jev and some other open decision models using the Jev Decision Index available on Hugging Face, and the company's own ranking suggests Clef is slightly slower than other open models, but more accurate, with Clef-flash just as accurate as most of the others, but far faster.
To be fair to the competition, Cloudflare self-reported its own scores against the benchmark, and they have yet to be reproduced for ranking on the official Decision Index. Cloudflare also ran Clef against TypeSafe's own benchmarks, and claimed it beat Jev in three out of four areas, only losing out on agent trace observability. Even if it were a bit slower or less accurate, Clef has another major leg up on Jev: It's not limited to classifying text -- it can also handle images and video. Additionally, Clef supports a 64k context window. Jev can also handle up to 64k tokens across a request, although its state plus longest individual question is limited to 32k.
As for its speed and capability, Clef moves fast. Cloudflare ran it against Jev and some other open decision models using the Jev Decision Index available on Hugging Face, and the company's own ranking suggests Clef is slightly slower than other open models, but more accurate, with Clef-flash just as accurate as most of the others, but far faster.
To be fair to the competition, Cloudflare self-reported its own scores against the benchmark, and they have yet to be reproduced for ranking on the official Decision Index. Cloudflare also ran Clef against TypeSafe's own benchmarks, and claimed it beat Jev in three out of four areas, only losing out on agent trace observability. Even if it were a bit slower or less accurate, Clef has another major leg up on Jev: It's not limited to classifying text -- it can also handle images and video. Additionally, Clef supports a 64k context window. Jev can also handle up to 64k tokens across a request, although its state plus longest individual question is limited to 32k.
Re:To be or not to be (Score:5, Funny)
Can it replace Hamlet?
It can, just not well.
The Headlines (Score:5, Funny)
"Cloudflare Tries to Outplay Jev With Open-Weight Clef Models"
The headlines get more incomprehensible every day.
Breaking News: "Frndo Shares Clarts with Carnob Twice; is Jorp Spivved??"
Re: (Score:2)
- did you order the code red?!?
Re: The Headlines (Score:2)
What is Jev / Clef? (Score:4, Informative)
For anyone else wondering what this is about.
Basically Jev is a layer (like a service) in an application which makes decisions and outputs a simple json which is used by the dev to carry out an actions. So essentially it takes unstructured data, and makes a decision like priority, or urgency, or apply a flag, etc.
So in a ticket system, to decide urgency and department;
Or in deciding whether a message posted on a board needs moderation or is harmful;
Or to monitor logs and decide on urgency of event, or to flag certain things;
Or to monitor and inform if an AI agent might perform a destructive operation.
Etc.
It doesn't itself carry out actions, only decide and output a structured json.
In short: unstructured input goes in, a constrained decision comes out, and the surrounding software decides what to do with it.
Re: (Score:2)
Jan wanted to eat darkness, but darkness ate him. Mayhaps some fragments of the doodlywinks still whimper?
Cloudflare! (Score:1)
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
What about the anime nurse one? At least you don't have to click on that. (Example: https://openwrt.org/ [openwrt.org])