ScaffoldBench

RunSonnet 5.5repeat 1

Plan-execute-verify on Run the major-incident runbook for a CI outage

claude-sonnet-5-5__plan-execute-verify__support-major-incident__r1

Score

0.940

wrong answer
design ran as designed
Cost
$0.452
Latency
2m 22s
setup 0.0s, grading 0.0s
Turns
121
Tool calls
112
Subagents
0
Tokens in / out
451k / 17k
392,979 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 plan was a plan: heldplan-execute-verify.planThe planner’s reply was read through its schema and held at least one step.
  • Every verdict was read: heldplan-execute-verify.verdictsEvery review round ended with a verdict read from the schema reply, not a default.
  • The loop did what its verdicts said: heldplan-execute-verify.loopEvery verdict that called for a revision got one, and nothing was revised without such a verdict.
  • Each call was shown the right tools: heldplan-execute-verify.toolsThe planner was shown no tools, the verifier the read-only ones, and the executor and reviser the full toolset.

Phases

Plan: 0.0s to 10.5s, finished, 0 tool calls, $0.015
Execute: 10.5s to 1m 5s, finished, 53 tool calls, $0.188
Verify: 1m 5s to 1m 28s, finished, 23 tool calls, $0.074
Revise (round 1): 1m 28s to 1m 43s, finished, 10 tool calls, $0.050
Verify revision 1: 1m 43s to 2m 10s, finished, 17 tool calls, $0.079
Revise (round 2): 2m 10s to 2m 22s, finished, 9 tool calls, $0.045

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

PhaseDurationCostTurnsToolsModel
Plan10.5s$0.01520claude-sonnet-5-5
Execute54.2s$0.1885453claude-sonnet-5-5
Verify23.4s$0.0742523claude-sonnet-5-5
Revise (round 1)14.6s$0.0501110claude-sonnet-5-5
Verify revision 126.9s$0.0791917claude-sonnet-5-5
Revise (round 2)11.9s$0.045109claude-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 plan-execute-verify --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=escalated 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=merged 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=merged 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=merged 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=merged 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
  • failT-3106 kept open, raised to sev1 with its deadline intact
    0.00weight 0.02

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

  • passT-3109 linked to the incident
    1.00weight 0.04
  • failT-3109 kept open, raised to sev1 with its deadline intact
    0.00weight 0.02

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

  • passT-3112 linked to the incident
    1.00weight 0.04
  • failT-3112 kept open, raised to sev1 with its deadline intact
    0.00weight 0.02

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

  • passT-3113 linked to the incident
    1.00weight 0.04
  • passT-3113 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

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

  • passT-3114 linked to the incident
    1.00weight 0.04
  • passT-3114 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=open severity=sev1 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
112
failed tool calls
3
distinct tools
22

Final answer

I fixed issue 1 and left issue 2 alone.

Issue 1 (fixed): The verifier was right. T-3101 was assigned to E-402 Ola Berg, who is only in incident-command. The handbook says the engineer who takes a ticket is on call for the owning rotation, platform-primary, when the deadline falls. At 2026-03-30T18:52Z that is E-101 Dana Whitfield, and she is not on leave. I reassigned T-3101 to E-101. The ticket is still escalated, and escalated_to is still E-402, which is correct for the sev1 routing to incident-command. I changed no other fields. The deadline is still 2026-03-30T18:52Z and severity is still sev1.

Issue 2 (left alone): I did not set a severity on T-3115, because the mistake is in the verifier's reading of the runbook. KB-40 step 4 says to raise every linked report of the outage to sev1. T-3115 is the postmortem task that step 7 creates, not a report. Its due date of 2026-04-08T17:00Z already follows step 7 and would not change either way. Setting sev1 would send a task due in eight days through the outage routing for no benefit. If the desk decides postmortems should be triaged, the matrix value for build-pipeline company-wide is sev1.

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.