LLMDEP Control Panel

Loading workspace...

Workspace Paths

Models

0

Benchmarks

0

Start Evaluation

Choose one model and one or more benchmarks. The task runs through gen_eval --evaluate.

Active Evaluations

Running and paused tasks from mep_client/log/task_records.json.

0
Run ID Status PID Benchmark Model Progress Subtask Started Actions

Completed Evaluations

Finished, failed, and manually cancelled tasks from mep_client/log/task_records.json.

0
Run ID Status Reason PID Benchmark Model Progress Subtask Started Actions