github / Research & data

jev-benchmark

AI-assisted summaries and translations. Check original sources for context and performance claims.

themsquared · Original language: English

This repository provides a reproducible benchmark for TypeSafe AI's Jev, evaluating its performance on agent tool-call risk classification. It specifically tests accuracy, latency, and the reliability of confidence scores across clear, ambiguous, and adversarial task scenarios.

Translated summary · AI-assisted; check the original.

Open original Copy linkSave

JEVLAB ART

Top 10

Sponsor

1. W
   Wallpets 91 clicks$125
2. W
   Walltank 107 clicks$85
3. C
   Chowder 59 clicks$50
4. F
   Falconer 50 clicks$45
5. L
   Lemonpod 90 clicks$40
6. M
   Menta 36 clicks$35
7. S
   Sway 34 clicks$30
8. P
   Peon-Ping 30 clicks$25
9. Z
   Zeron 92 clicks$20
10. G
    Guideless 25 clicks$15

Sponsor