HERMES BENCHMARKS // FLEET TELEMETRY

BOOTING awaiting uplink

30-DAY TOKEN FLOW

INOUTKANBAN DONE

MODEL LEADERBOARD

    KANBAN THROUGHPUT

      TOP ASSIGNEES

        GRADES

          PROFILE REPORT CARDS

          CRON RELIABILITY

            HOW GRADING WORKS

            rubric v1 · refreshed every 5 min
            40%KANBAN OUTCOMESfirst-pass, reopens and blocked cards on completed work
            20%CRON RELIABILITYsuccess rate of scheduled job runs
            20%BLIND REVIEWan LLM judge from the default profile scores output against the brief — the doer's model is hidden
            20%PROVING GROUNDfixed bench tasks with deterministic pass/fail checks

            Composite = weighted mean over the tiers a model actually has, weights renormalised. Grades: A ≥ 90 · B ≥ 80 · C ≥ 70 · D ≥ 60 · F below. PROVISIONAL marks a small sample — treat the letter as a lead, not a fact.

            CREW ROSTER

            CRON HEALTH

            —

            LAST 24 HOURS