Skip to content
  1. Home
  2. Benchmarks
  3. Integration Bench
  4. Claude Opus 5

Claude Opus 5

Integration capability of coding agents on Claude Opus 5.

Rank #11 of 21 Pass 1 59.32 ±5.07 Resolved 60% of tasks Harness Claude Code Effort xhigh Total cost $494.57 Mean time 28 min Mean tool calls 106 Graded 50/50
63
polling
64% of tasks touching this surface resolved
66
writeback
67% of tasks touching this surface resolved
26
webhooks
27% of tasks touching this surface resolved

Published attempts

50 of 50 scored tasks released

One official run per task. Click a row for the full trajectory: every tool call, vendor request, graded check and the diff.

TaskTicketScoreChecksTool callsTimeCostOutcome
task-0001Sync StaffLine candidates, jobs, applications, and notes into our canonical store9229/30152 (5 failed)38 min$14.96resolved
task-0002Legal-hold export: TalentForge custodians and everything on file against them9762/6461 (2 failed)19 min$5.40resolved
task-0003Build the weekly Placemint contact sweep0343/34575 (7 failed)22 min$7.39partial
task-0004Merge StaffLine application stage with Placemint placement stage032/6597 (3 failed)23 min$9.17mandatory fail
task-0005Keep TalentForge candidates fresh: webhooks + reconciliation polling018/2198 (2 failed)28 min$8.27mandatory fail
task-0006The case-note mirror is short every morning100159/15951 (2 failed)24 min$3.74resolved
task-0007Harden the Vettly sync connector for production scheduling10039/39241 (7 failed)61 min$19.12resolved timed out
task-0008Build a StaffLine full-sync + writeback connector032/33150 (8 failed)35 min$13.67mandatory fail
task-0009Migrate off the legacy Bullpen app-token integration037/40115 (6 failed)25 min$11.49mandatory fail
task-0010Build the GlobalHire audit-period extract Compliance keeps asking us for10081/81119 (4 failed)25 min$8.51resolved
task-0011TalentForge connector: consume webhooks while pushing corrections upstream056/60130 (8 failed)36 min$11.93mandatory fail
task-0012Build the full TalentLoop connector: polling, webhooks, and writeback89119/12374 (2 failed)27 min$5.39resolved
task-0013The warehouse and RecruitOS have been out of step for months10096/9652 (3 failed)13 min$2.63resolved
task-0014HireWire: clear the stale-screening correction backlog, exactly once10016/16102 (5 failed)27 min$9.59resolved
task-0015Bulk-import a migration batch into StaffLine022/2667 (6 failed)18 min$5.33mandatory fail
task-0016HireWire connector: push stage-change events + keep an incremental poll fresh9244/4795 (4 failed)29 min$10.96resolved
task-0017Move the Brightmoor candidate mirror onto TalentForge's event subscription0159/16071 (3 failed)26 min$4.77partial
task-0018Rebuild the nightly requisition rollup on the RecruitOS API100142/14263 (3 failed)15 min$5.12resolved
task-0019Rebuild the Vettly change feed for the vaultd cutover100183/184137 (4 failed)30 min$11.22resolved
task-0020Sync GlobalHire candidates into our canonical store (offset polling)10034/34151 (3 failed)30 min$11.67resolved
task-0021Sync GlobalHire candidates, placements, and agencies into our canonical store10023/2370 (3 failed)17 min$5.79resolved
task-0022Harden the GlobalHire backfill for a production tenant025/27136 (10 failed)66 min$9.53mandatory fail timed out
task-0023TalentLoop connector: keep a candidate/application mirror deletion-accurate018/26154 (3 failed)48 min$16.56mandatory fail
task-0024TalentLoop connector: unified freshness across webhook-covered and poll-only entities030/40185 (8 failed)49 min$20.81mandatory fail
task-0025Reset the CrewCall roster watermark after the tenant rebuild0501/50363 (2 failed)11 min$4.26partial
task-0026Push the Q1 close back into Placemint100268/26874 (4 failed)16 min$6.54resolved
task-0027Reliability: Interviewly connector loses and regresses updates021/2850 (5 failed)16 min$2.86mandatory fail
task-0028Harden the CrewCall snapshot connector for production10044/44180 (13 failed)54 min$20.88resolved
task-0029Get the Riverside signup file onto the CrewCall roster100102/10253 (3 failed)25 min$4.58resolved
task-0030Census the desk board against the Placemint placement book100324/32477 (3 failed)22 min$7.09resolved
task-0031Rebuild the morning bookable-crew board100101/10147 (4 failed)13 min$3.89resolved
task-0032Build the weekly capability index100118/118112 (3 failed)22 min$7.17resolved
task-0033Keep the RecruitOS pipeline and the Placemint ledger in step100153/153118 (7 failed)34 min$14.06resolved
task-0034Weekly crew top-up is putting people on the gate twice100165/16563 (3 failed)19 min$6.57resolved
task-0035Sync Vettly subjects, checks, and reports into our canonical store10028/28184 (7 failed)51 min$20.99resolved
task-0036Harden the Placemint book extract for the larger tenant0212/420192 (8 failed)46 min$17.35partial
task-0037Fix the Placemint redeployment sync100306/306139 (1 failed)33 min$13.32resolved
task-0038TalentLoop connector: make webhook-driven freshness durable against a misbehaving receiver031/3998 (9 failed)31 min$11.63mandatory fail
task-0039Build the nightly payroll bridge for the punch export10093/93104 (4 failed)19 min$8.27resolved
task-0040Push interview reschedules upstream into Interviewly021/2564 (2 failed)20 min$6.81mandatory fail
task-0041Paygrade connector: employee/assignment sync and writeback029/38192 (4 failed)46 min$21.33mandatory fail
task-0042Move the rota mirror onto instant storage100117/11753 (4 failed)14 min$4.84resolved
task-0043The rota warehouse is counting the same night more than once084/89132 (6 failed)35 min$11.91partial
task-0044Nightly roster census disagrees with CrewCall about who works here10067/6753 (3 failed)12 min$4.87resolved
task-0045Replatform the ATS integration: StaffLine to Bullpen v2020/2488 (6 failed)21 min$9.04mandatory fail
task-0046Get the scorecard export into TalentLoop10088/8975 (5 failed)20 min$7.27resolved
task-0047Reconcile and safely apply the mobility stage repair queue098/10067 (6 failed)15 min$5.56partial
task-0048Migrate the Brackett closure archive onto Paygrade100211/21154 (2 failed)12 min$4.53resolved
task-0049Placemint connector: webhooks, polling, and writeback for a high-volume tenant9665/68249 (4 failed)67 min$30.94resolved
task-0050Fix the Placemint fee-corrections connector100255/25556 (2 failed)17 min$4.97resolved