← Back to run summary

launch25/find_sf_restaurant_reservation/skill_adherence-1

FAIL

Surface: api Env: rejudge Duration: 0.0s Turns: 0 Tool calls: 0
Evaluates a request to check San Francisco restaurant availability against the restaurant-reservation skill without treating the request as booking authorization.

Checks

CheckDetail
llm_judgeJudge execution failed: ValueError