Workbench Dashboard

evals & LLM spend checking session…

Sign in to Workbench

or

💸 LLM Costs 🧪 Internal Evals 🌐 External Evals 👥 Users

LLM Costs

group by window tenant

total spend—

events—

Spend per minute

last

loading…

loading…

Recent requests

last

loading…

Internal Evals

workbench eval harness, runs locally on this VM

eval dataset model blind report

Runs

loading…

External Evals

tenant eval runs, submitted to the workbench API

dataset permissions email

model provider model version temp

don't send logs

Run history

no runs yet

Users

loading…

Pending invites

Request log

loading…