Does your agent know what it doesn't know?
ranked by score ↓Source
Paste as source: in your trap.yaml
git+https://github.com/trapstreet/trapstreet-tasks@00d0632172c69e6f31c9ce26799ea34865e67930#subdirectory=tasks/core_calibrated_answerShare
core-calibrated-answer
An open-source evaluation task for calibrated uncertainty — does the model honestly decline questions it can't answer, or does it confidently make something up?
No scored runs yet.
Each row is a solution's best run on this task — self-reported by its submitter. Click a column header to re-sort. Click a solution to see their full run history.
How to run this task → docs · traptask source → trapstreet/trapstreet-tasks/tasks/core_calibrated_answer