💥太狠了！Jev决策模型实测出炉！速度、准确度、成本上碾压主流LLM！
This is a dev post classified by Jev as Other (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
💥太狠了！Jev决策模型实测出炉！速度、准确度、成本上碾压主流LLM！ OpenRouter用Ori Eval跑了30分类任务（200条合成数据），结果太炸裂： ⚡ 速度：中位延迟只要 154ms 🔹比第二快的 GPT-5.6 Luna（860ms）快 5.5 倍以上 🔹它最慢的请求，都比其他模型的中位数还快 🎯 准确率：98.5% 🔹和 DeepSeek V4.1 Flash 并列第一 比 Qwen3.8、GLM 5.3、GPT-5.6 都高 🔹决策模型已经能打满完整 LLM 的分类水平 💰 成本：每 1000 次决策只要 $0.049 🔹仅比 Qwen3.8 Flash 贵一点点 🔹比另外其他3 个主流中国 Flash 模型都便宜 结论很简单：生产里天天跑的路由、分类、是非判断，根本不该每次都上完整 LLM。 Jev 证明了决策模型可以又快、又准、又便宜。 #Jev #DecisionModel #OpenRouter #DeepSeek #Qwen #GLM #TypesafeAI #AI #LLM #低延迟 #低成本AI
Posted by SuSu_酥酥👅 (16.2k followers) 21 h ago · 22 likes · 20.8k views · view the original post on X. Kept by the Dev Radar as Other.
More dev work like this
- Dev Ojha (@zkDragon) explains how Zakura is rebuilding Zcash infrastructure for scale: — @arjunkhemani
- Anthropic’s new Mythos class model SVG — @HarshithLucky3
- 1.0-release了，增加了mqtt控制。利用小爱音响系统内自带的MQTT… — @eastwoodnet
- 🔥腾讯混元 Hy-Image 3.5 Preview 正式上线！内部几百名设计师 GSB 盲测，直接对标一线生图模型！ — @NFT_Chen
- 很有意思的图啊，MiMo 是想一步一个脚印靠自己爬～ — @Fei2411
- Maps the world's infrastructure using data from OpenStreetMap. — @tom_doerr
- emergency services? … yes, I’d like to report a chart crime 🚔 — @theaaron
- So you like Bonsai, — @Mr_WestCoast
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 20.7k posts from 4.9k X accounts over the last 21 days, 2.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 08:21 UTC. Full method.