# Bailey Jennings compares Jev and Luna on ONET job classification

In a quick demo, TypeSafe AI's Jev scored 80.5% exact at about 200 milliseconds and $122 per 1M, against Luna's 84.9% exact at about 2 seconds and $482 per 1M.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-10T07:30:00.000Z
Query date (America/Los_Angeles): 2026-11-09

HTML: https://didcodexreset.com/news/d80e64c1424d4eefafb0f7b0.html

Content language: en
Localization state: sameLanguage

Source: Bailey Jennings · Published 9/22/2026, 15:33:24

Bailey Jennings ran a quick demo of TypeSafe AI's Jev against Luna on ONET job classification. Luna reached 84.9% exact, about 2 seconds per job, and $482 per 1M. Jev reached 80.5% exact, about 200 milliseconds per job, and $122 per 1M.

He summed up the difference as roughly 10 times faster and 4 times cheaper for about 4 points of accuracy.

Tags: Jev, Luna, TypeSafe AI, ONET, Benchmark

[View original post](https://x.com/Bailey_Jennings/status/2100593904949096696)