▌system-one

~ / benchmarks / probes-studies / janus

Janus

Measures a confidence threshold on your labeled data, then routes Jev vs a larger model. Ships no default: on Banking77 routing wins; on Web of Science it says do not route.

section
Benchmarks
group
Probes & studies
source
github.com
repo
firassx914/janus
stars
2 ▕█░░░░░░░░░░░▏
7-day gain
0
forks
0
language
Python
license
MIT
last pushed
oct 5
added to list
sep 20

## history

2026-09-130 → 2 stars2026-10-13

also in Probes & studies