All Tasks

Loading metrics files...

Mode: none | Files: 0 | Warnings: 0

Total Runs

-

Total Tasks

-

Best Accuracy

-

Total Requests

-

Leaderboard (Selected Task, Grouped by Model)

Best Run Per Task

Token / Request Signals (Selected Task, Sortable)

Runs

Task Model Timestamp Accuracy Macro F1 Requests Cached Input Tokens File