Benchmark report

Task verified

3m 44s elapsed

The saved attempt met the documented success criterion.

Experience score

100/ 100

Agent-Ready
  • SInstall
  • SAuth
  • SExecute
  • SDocs
  • SCurrent
Experience measures friction in the tested task. The verdict says whether it succeeded.
Agent profile for this run: Install S, Auth S, Execute S, Docs S, Current SSInstallSAuthSExecuteSDocsSCurrent
Agent profile · this run
Judge's note · what slowed the agent most
Essentially nothing; the only hiccup was a 404 on a guessed https://agentmail.to/auth.md URL fetched in parallel, which cost no time.

Where the time went

3:45 agent time
  • Research0:20
  • Attempt2:03
  • Verify1:22
3m 44sTotal elapsed
1:19Time to first success
0:00Waited on the owner

Judge reason

Saved code (agentmail-domain/domain_flow.py) runs the full lifecycle against https://api.agentmail.to/v0 with Bearer auth, and evidence/transcript.json + run_output.txt (echoed verbatim in the transcript at the run step) show real responses: POST /v0/domains -> HTTP 200 creating tpc-bench-39871c28.example.com with domain_id and 5 DNS records (DKIM TXT, 2 MX w/ priority 10, SPF TXT, DMARC TXT), GET /v0/domains/{id} -> 200 with records each status MISSING, POST /v0/domains/{id}/verify -> 204, GET again -> 200 status PENDING reason dns_records_missing, DELETE -> 204, final GET -> 404 NotFoundError code not_found. Report lists every record type/name/value and reports PENDING, never claiming verified. No dashboard or SMTP, no mocks or hard-coded responses (live org/pod UUIDs, server timestamps, real DKIM key).

Attempt record

  1. 1:03Answered from saved key: AgentMail API keyno wait
  2. —First success verified

Attempt artifacts saved.