Routes Financial Complaints with Jev

梭哈.AI tested TypeSafe Jev (jev-latest) on 1,000 CFPB consumer complaints, routing them in real time to 15 financial business departments. It reported Jev accuracy of 90%~95% on core business tasks and 70%~100% on complex long-text filtering.

View on X cost$0.146time33.5 S; 368ms

梭哈.AI@SUOHA_AI𝕏

Jev要被开源模型干掉了？我来实测两个决策模型的能力，到底有没有吹牛？ Jev 实际上不应该跟LLM相比，要测就得找同一个生态位的对手！于是我找到了同样是决策模型的 FLock——一个超轻量级的决策模型，而且完全开源免费为了不测垃圾数据，我从美国消费者金融保护局（CFPB）公开数据库摘了 1,000 条真实的真人长篇控诉（包含真实口语、愤怒投诉、维权错字以及乱码垃圾单），同时喂给这两个主打毫秒级决策的模型，实时分流到 15 个细分金融业务部门👇 左边：TypeSafe Jev（jev-latest）右边：FLock（this-that-model-1.0）（开源免费） ─── 具体正确率表现如下 ─── • 日常核心业务 │ Jev: 90%~95% │ FLock: 85%~98% （双方差距不大） • 复杂长文过滤 │ Jev: 70%~100%│ FLock: 14%~61%（Jev占优） • 决策时间对比 │ Jev:33.5 S │ FLock: 36.1S （Jev占优） • API响应速度 │ Jev: 368ms │ FLock: 405ms （双方差距不大） • 官方API 成本 │ Jev: $0.146│ FLock: $0 （Flock成本完胜） ──────────────────────── 客观总结： Jev @typesafeai 在“复杂问

Sep 23, 2026X postsView on X

The test compared Jev with the open-source FLock model using the same complaints, which included colloquial language, typo-filled complaints, and junk entries. The author also reported Jev’s decision time, API response speed, and official API cost.

Also filed under Triage & routing

How to Build Things with Jev & OpenJevs
How to Build Things with Jev & OpenJevs In this video, we build a model router using both the API-based original Jev and also using Semif. ‍ Github: code will be up in ...
Jev is HERE. How to use it
Jev is HERE. How to use it In this episode, I talk with Ryan Vogel about Jev, a new type of AI built for classification. Ryan shows how Jev takes an input plus ...
Jev-Shaped Classification Wrapper
jevper is a Jev-shaped classification wrapper over OpenAI-compatible clients that returns probabilities and confidence.
Local Jev Protocol Multi-Upstream Router
jev-switch is a local multi-upstream router for the Jev protocol with a Rust backend and React interface.