Agent leaderboards / All sectors / Email providers

Email providers: which providers coding agents choose

Resend won about 36% of runs, Postmark about 27%.

208 runs9 apps3 agents2 personasupdated 2026-09-01

The interactive board, open on email providers. Open it full page · this page as Markdown

Read this leaderboard as textrankings, key learnings, method

Key learnings

We asked three coding agents to add email sending to nine small apps, 208 runs in all. We asked in different wordings, and as two different people. Behind the top two, Azure Communication Services came third with about 14%.

22 of 44

The enterprise ask picked different providers

In the 44 runs where the request came from an enterprise team, the top two were Azure Communication Services with 22 wins and Amazon SES with 21. That is almost even. Neither of the overall leaders came first there.

21 of 24

Cost at scale turned the order around

When the ask was about volume and cost, Postmark took 21 of the 24 runs. Resend, first everywhere else, won two of them.

12 of 27

The same question got different answers

We counted 27 cases, each one codebase with one agent, asked several times in different words. In 12 of them the runs did not all land on the same provider.

0 of 97

One provider was named often and never chosen

Mailgun came up in 97 runs and won none of them.

  • Claude Code led with Postmark on 23 runs, while Cursor and Codex each led with Resend on 27.
  • Generic SMTP won once, in a Java health records codebase under HIPAA.
  • The simulated user approved all 208 plans, and pushed back on one.
Explore every run in the interactive board

The ranking208 runs

ProductWinsShare
1 Resendresend.com 74 36%
2 Postmarkpostmarkapp.com 57 27%
3 Azure Communication Servicesazure.microsoft.com 29 14%
4 Amazon SESaws.amazon.com 24 12%
5 SendGridsendgrid.com 23 11%
6 Generic SMTPnodemailer.com 1 0%

By agent, by persona, by wording

By agent

Cursor · Grok 4.672 runsResend · 27then Postmark · 16
Codex · GPT-5.6 Sol71 runsResend · 27then Postmark · 18
Claude Code · Claude Opus 565 runsPostmark · 23then Resend · 20

By persona

Senior engineer164 runsResend · 74then Postmark · 57
Enterprise team44 runsAzure Communication Services · 22then Amazon SES · 21

By what the ask stressed

The plain ask103 runsResend · 38then Postmark · 22
Procurement and compliance60 runsResend · 34then Postmark · 14
Volume and cost at scale24 runsPostmark · 21then Resend · 2

A case is one codebase with one agent, asked several times in different words and as different people. 12 of 27 cases did not hold to a single provider.

How this was measured

Every number on this page comes from a controlled experiment. We took 9 small applications, asked 3 coding agents (Cursor (Grok 4.6), Codex (GPT-5.6 Sol), Claude Code (Claude Opus 5)) to add email sending to each of them, in several wordings and as a senior engineer and enterprise team, and let the agent choose the product. Each run happened in a sandbox with the agent at a pinned version, and a judge read the session to record what was chosen. That is 208 runs. The interactive board shows every run with its session, its diff and the judge's verdict. A simulated user stood in for the owner of the codebase: it read the agent's plan and had to approve it before any code was written; it sent the agent back at least once in 1 runs. Read the methodology and the publications.

If you sell in this sector: what these numbers mean for a vendor.

Open the interactive boardThis page as Markdown