Jev Classifies 11,000 Legal Docs at 16.5 per Second, 495K Document-Question Checks
TheMoonMidas · x · 2026-09-17
@gmarquezp used Typesafe's Jev to classify 11,000 legal documents across 45 questions at 16.5 documents per second—roughly 495,000 document-question checks. He calls it fast, well-calibrated and inexpensive, though no accuracy breakdown has been published yet; the scale itself is the headline.
More from Models
- TypeSafeAI launches Jev, a foundation model claiming 20-200x speed and 40-400x cost gains — hardimanjames · 2026-09-17
- Burkov: OpenAI wouldn't kill the 20x plan if it were profitable, the 5x plan is likely borderline too — burkov · 2026-09-17
- Dev calls for speed/productivity benchmarks: frontier LLMs still ship with no sense of time — gandamu_ml · 2026-09-17
- Heavily Quantized Qwen 3.8 27B Taught Itself to Drive Headless Chrome for Testing — satnl · 2026-09-17
- Garry Tan says Grok bot is broken for him, unresponsive across X, Cursor and GitHub logins — garrytan · 2026-09-17
- Teknium challenges critics: replicate a full repo faster and cheaper in one agent session — Teknium · 2026-09-17