Cloudflare Workers has Jev now so I'm putting it to the test on keep.md - 7x faster search rerank compared to the current hybrid - 50x faster tagging of content vs GLM 4.7 Flash with no failures
CommunityPractices & Patterns
Jev in Search: Three Practical Evaluations
An independent evaluation of Jev in three retrieval stacks, with recalculated recall, latency, and cost against DeepSeek, GPT-4o-mini, and GPT-5-mini baselines.
- Category
- Practices & Patterns
- Format
- Article
- Published by
- Community
- Author
- Cheney Zhang
- Added
- 2026-09-25
- Last verified
- 2026-09-25
Highlights
- In DeepSearcher both Jev and DeepSeek V4 Flash hit 93.25% Recall@5, while decision latency fell from 2.23 s to 0.55 s.
- On 2,172 MemSearch questions Jev lifted Recall@5 from 74.71% to 79.41%, behind Voyage rerank-3 at 81.87%.
- On Vector Graph RAG Jev beat GPT-4o-mini but trailed GPT-5-mini by 1 point on MuSiQue and 4.13 on HotpotQA.
- Jev cost about $3.15 per 1,000 questions against $6 to $9 for GPT-5-mini.
Watch out
The author works on the evaluated projects, and baselines reuse published 1,000-question results against Jev's 500-question samples, so the comparisons are not paired tests.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Search and tagging on keep.md
X: Jev reranks station suggestions in TrainLCD
提案駅のリランク判定と実測スパイクを追加する by TinyKitten · Pull Request #33 · TrainLCD/Functions github.com/TrainLCD/Funct… AIチャット機能の一部にもJevを潜ませてみるゾ
YouTube: Jev in the reranking step of a RAG pipeline: why cosine similarity fails and how a steerable reranker compares. A Colab notebook comes with it.
X: Natural-language search over Zillow
Jev can serve as better natural language search on websites. It can scan thousands of Zillow listings and classify properties by things you can't normally filter for - e.g. architecture, renovation status, proximity to freeways. This was done in <20 sec and costs $0.18 👇
More like this
9GitHub stars
A graded relevance evaluation of Jev as a reranker: 9,831 labelled pairs from 164 queries over a 33,047-item skills catalog, comparing Jev score reranks with BM25, bge-m3, and rank fusion.
Practices & Patterns#community#python#search
8GitHub stars
Reranking benchmark that gave Jev, Cohere Rerank 4 Pro, ZeroEntropy zerank-2, and DeepSeek the same thirty BM25 candidates across eight English datasets, publishing saved responses, scoring code, and paired-bootstrap intervals. Jev's rubric scored 0.692 nDCG@10 against Cohere Pro's 0.691.
Practices & Patterns#community#python#search
Community
anessbelbati/jev-rerank-benchPython
anessbelbati/jev-rerank-benchPythonA measured search reranking run over 33,047 catalog entries, 164 real queries, and 9,831 labelled pairs, reporting how Jev compares with BM25 and bge-m3.
Practices & PatternsPost#community#x#search
Community
From the community
Posts from builders shipping with Jev right now.
Security decisions that fit Jev
This made me rethink where AI actually fits into security engineering. For purely engineering work, forget about ChatGPT or Claude. TypeSafe AI just released Jev, and I think it’s going to change how we build AI into security workflows. Instead of asking an LLM to “investigate Show more
we are officially out of stealth! join the frontier and get access to Jev on our website (link on profile)
A million judged questions
Ask Jev anything. Give it a try at askjev.ai It won't answer. It will judge. Let's see if we can get to 1 million questions. @typesafeai 🤝 @convex work great together. @hmartenjoyer @CompleteSkeptic @justKDeng @mikeysee
Inferring Jev's internals from 1,000 calls
Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more
The open System One roundup
Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more
Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格
Jev lands on the Vercel AI Gateway
Jev is now available on the @vercel AI Gateway vercel.com/ai-gateway/mod…
Vercel ships the AI SDK provider for Jev
Jev from @typesafeai is on AI Gateway. Build agents that decide, route, score, and stop in milliseconds: 𝚊𝚠𝚊𝚒𝚝 𝚎𝚟𝚊𝚕𝚞𝚊𝚝𝚎({ 𝚖𝚘𝚍𝚎𝚕: '𝚝𝚢𝚙𝚎𝚜𝚊𝚏𝚎-𝚊𝚒/𝚓𝚎𝚟', 𝚜𝚝𝚊𝚝𝚎, 𝚚𝚞𝚎𝚜𝚝𝚒𝚘𝚗𝚜, }); vercel.com/changelog/type…