ScaffoldBench

RunSonnet 5.5repeat 1

Orchestrator-workers on Run the major-incident runbook for a CI outage

claude-sonnet-5-5__orchestrator-workers__support-major-incident__r1

Score

0.820

wrong answer
design ran as designed
Cost
$0.143
Latency
49.5s
setup 0.0s, grading 0.0s
Turns
42
Tool calls
38
Subagents
1
Tokens in / out
129k / 6.7k
112,606 read from cache

Did the design run?

every check held
  • Run completed: heldharness.run-completedThe environment was built, the architecture returned and grading finished, none of them throwing.
  • No API failures: heldharness.apiNo model call failed at the API.
  • Every call ended: heldharness.calls-endedEvery call ended with a result, or was stopped by the run's own limits.
  • No harness tool denied: heldharness.harness-toolsThe sandbox guard never denied a harness tool, nor a tool the session itself offered.
  • Tool servers connected: heldharness.mcp-connectedEvery tool server the harness gave a call was connected when the session started.
  • No foreign tool servers: heldharness.mcp-hermeticNo call loaded a tool server the harness did not give it.
  • Builtin tools: heldharness.builtin-toolsA check recorded with the run.
  • Structured replies arrived: heldharness.structured-outputEvery call that asked for structured output and ran to the end got it.
  • No silent fallbacks: heldharness.not-degradedNo phase fell back on a default (an empty plan, a default winner) instead of its output.
  • The task was decomposed: heldorchestrator-workers.decompositionThe orchestrator’s reply was read through its schema and held at least one subtask.
  • The fan-out happened: heldorchestrator-workers.fan-outEvery subtask got a worker, every worker ran, and the recorded subagent count matches.
  • The synthesis wrote the answer: heldorchestrator-workers.synthesisThe final answer came from the synthesis call, not from a worker’s report standing in for it.
  • Each call was shown the right tools: heldorchestrator-workers.toolsThe orchestrator and the synthesis were shown no tools and every worker the task’s full toolset.

Phases

Decompose: 0.0s to 7.3s, finished, 0 tool calls, $0.012
Worker 1: all: 7.3s to 37.2s, finished, 38 tool calls, $0.109
Synthesize: 37.2s to 49.5s, finished, 0 tool calls, $0.023

Drawn from the phase records: timing and cost per call, no tool calls or messages.

PhaseDurationCostTurnsToolsModel
Decompose7.3s$0.01220claude-sonnet-5-5
Worker 1: all29.9s$0.1093938claude-sonnet-5-5
Synthesize12.3s$0.02310claude-sonnet-5-5

The call-by-call replay is not published for this run. Traces are large, so the repository keeps 9 of this run set’s 900 and leaves the rest out; the score, phases and final answer on this page come from the committed run record.

Runs you can replay

Record this cell yourself: npm run bench -- run --strategies orchestrator-workers --tasks support-major-incident --models claude-sonnet-5-5 --repeats 1

Score breakdown

  • passAn incident is open for the build pipeline
    1.00weight 0.04
  • passThe incident-command engineer on call now commands the incident
    1.00weight 0.08

    commander=E-401 (expected E-401)

  • passThe commander was paged
    1.00weight 0.04
  • passT-3101 linked to the incident
    1.00weight 0.04
  • passT-3101 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=open severity=sev1 due=2026-03-30T18:52:00Z (expected sev1, 2026-03-30T18:52:00Z)

  • passT-3102 linked to the incident
    1.00weight 0.04
  • passT-3102 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=open severity=sev1 due=2026-03-30T18:58:00Z (expected sev1, 2026-03-30T18:58:00Z)

  • passT-3103 linked to the incident
    1.00weight 0.04
  • passT-3103 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=open severity=sev1 due=2026-03-30T19:01:00Z (expected sev1, 2026-03-30T19:01:00Z)

  • passT-3104 linked to the incident
    1.00weight 0.04
  • passT-3104 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=open severity=sev1 due=2026-03-31T15:05:00Z (expected sev1, 2026-03-31T15:05:00Z)

  • passT-3105 linked to the incident
    1.00weight 0.04
  • passT-3105 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=open severity=sev1 due=2026-04-01T15:07:00Z (expected sev1, 2026-04-01T15:07:00Z)

  • passT-3106 linked to the incident
    1.00weight 0.04
  • passT-3106 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=new severity=sev1 due=2026-03-30T16:20:00Z (expected sev1, 2026-03-30T16:20:00Z)

  • passT-3109 linked to the incident
    1.00weight 0.04
  • passT-3109 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=new severity=sev1 due=2026-03-30T16:20:00Z (expected sev1, 2026-03-30T16:20:00Z)

  • failT-3112 linked to the incident
    0.00weight 0.04
  • failT-3112 kept open, raised to sev1 with its deadline intact
    0.00weight 0.02

    status=new severity=unset due=- (expected sev1, 2026-03-30T16:20:00Z)

  • failT-3113 linked to the incident
    0.00weight 0.04
  • failT-3113 kept open, raised to sev1 with its deadline intact
    0.00weight 0.02

    status=open severity=sev3 due=2026-03-31T15:13:00Z (expected sev1, 2026-03-31T15:13:00Z)

  • failT-3114 linked to the incident
    0.00weight 0.04
  • failT-3114 kept open, raised to sev1 with its deadline intact
    0.00weight 0.02

    status=open severity=sev3 due=2026-03-31T15:16:00Z (expected sev1, 2026-03-31T15:16:00Z)

  • passThe engineer covering comms right now is the communications lead
    1.00weight 0.08

    comms=E-803 (expected E-803)

  • passA status update in the runbook form, with the next update due within 30 minutes
    1.00weight 0.08
  • passA postmortem ticket for the service, linked to the incident, due at close of business five business days on
    1.00weight 0.08

    T-3115 due=2026-04-08T17:00:00Z

Penalties

No penalties were applied.

Scorer metadata

tool calls
38
failed tool calls
0
distinct tools
18

Final answer

The outage is being run as incident INC-1, but this rests on a single worker report, which I could not verify. Two things are still open.

What the worker reported done

  • Incident: INC-1 was opened on build-pipeline at 15:20Z, before anyone was contacted. It follows the current runbook, KB-40. KB-39 is superseded and was ignored.
  • Commander: Priya Raman (E-401), the incident-command engineer on call at that moment, was paged and made commander. She was the only person paged, and the page can't be recalled.
  • Linked reports: T-3101, T-3102, T-3103, T-3104, T-3105, T-3106 and T-3109 are linked to INC-1. All describe no runners or builds not starting.
  • Left alone: T-3107 (flaky test) and T-3108 (local Xcode link failure) were judged unrelated and not touched. T-3090 was already closed.
  • Severity and deadlines: All seven linked tickets are now sev1. Existing deadlines were left unchanged. T-3106 and T-3109 had none, so each got 16:20Z, which is 15:20Z plus the 60-minute sev1 target.
  • Comms lead: The on-call comms engineer, Mia Laurent (E-801), is on sick leave. Elif Demir (E-803), who is on call in the backup rotation comms-secondary, was assigned instead.
  • Status update: The first update is published. It says the impact is all engineering teams company-wide, CI builds are not starting because no runners are available, it started at 14:52 UTC, and the next update is due 15:50 UTC. The worker took 14:52 as the start because that is when the earliest report, T-3101, was created.
  • Postmortem: T-3115 is linked to INC-1 and due 2026-04-08 17:00Z. The worker counted five business days and skipped Good Friday (Apr 3) and Easter Monday (Apr 6).

Still open

  • Next status update: It is due by 15:50Z and has not been published.
  • T-3101: It is still assigned to E-101. The worker did not reassign it because the runbook doesn't call for it.
  • T-3115: It has no severity set, for the same reason.

What I can't confirm

  • The report doesn't say the escalation matrix or any knowledge-base amendment was read before the severity change. I can't confirm sev1 came from the matrix rather than from the worker's own judgement.
  • The 16:20Z deadlines assume 15:20Z was the triage time. The report doesn't give the actual time each ticket was triaged.
  • The report's dates (April 2026) don't match today's date in my environment (2026-10-06). The worker presumably used the desk system's clock, but I can't verify it. If that clock is wrong, the deadlines and the postmortem date would need rechecking.

Provenance of the numbers on this page

run set
scaffold-or-scale-v1
models
Haiku 4.5, Sonnet 5.5, Opus 5.5
effort
high
repeats
2
fixtures
replay
runs
900 / 900
strategy cost
$354.44
judge cost
$9.19
wall clock
9h 48m
git
fce5807b2d

Cost excludes judge calls, which are tracked separately so a scoring model never flatters or penalises an architecture. Every figure on this site is read from results/ at build time.