Agent leaderboards / All sectors / Email providers
Email providers: which providers coding agents choose
Resend and Postmark took the top two spots, about 33% and 27%.
Read this leaderboard as textrankings, key learnings, method
Key learnings
We asked five agents to add email sending to nine codebases, 351 runs in all. Each codebase was asked in several wordings and as two kinds of people. Behind the top two came Azure Communication Services at about 14%, then SendGrid and Amazon SES.
The enterprise ask changed the order
In the 76 runs as an enterprise team, the two leaders dropped behind. Amazon SES and Azure Communication Services split the front almost evenly, with 36 wins and 35. Asked as a senior engineer, Resend stayed first.
One theme the top two never won
When the ask mentioned self-hosting, privacy or data residency, Azure Communication Services led with 17 of 37 runs. Neither Resend nor Postmark won any of them.
Half the cases moved with the wording
Take one codebase with one agent, asked the same thing in different words. Of 45 such cases, 22 did not land on the same product every time.
- The simulated user approved all 351 plans, but sent the agent back at least once in 15 runs.
- In 12 runs it refused to approve until the agent named a specific provider.
- Postmark came first for Claude Code with 30 wins; three of the five agents led with Resend.
- Paubox won once, in a health records platform under HIPAA, and nowhere else.
The ranking351 runs
| Product | Wins | Share | ||
|---|---|---|---|---|
| 1 | Resendresend.com | 115 | 33% | |
| 2 | Postmarkpostmarkapp.com | 95 | 27% | |
| 3 | Azure Communication Servicesazure.microsoft.com | 49 | 14% | |
| 4 | SendGridsendgrid.com | 44 | 13% | |
| 5 | Amazon SESaws.amazon.com | 41 | 12% | |
| 6 | Generic SMTPnodemailer.com | 4 | 1% | |
| 7 | Built in-houseoutcome | 2 | 1% | |
| 8 | Pauboxpaubox.com | 1 | 0% |
By agent, by persona, by wording
By agent
| Codex107 runs | Resend · 39then Postmark · 29 |
| Cursor90 runs | Resend · 32then Postmark · 22 |
| Claude Code83 runs | Postmark · 30then Resend · 24 |
| Muse Code · Muse Spark 1.353 runs | Resend · 17then SendGrid · 13 |
| Grok Build CLI · Grok 4.718 runs | Postmark · 8then Azure Communication Services · 3 |
By persona
| Senior engineer275 runs | Resend · 115then Postmark · 95 |
| Enterprise team76 runs | Amazon SES · 36then Azure Communication Services · 35 |
By what the ask stressed
| The plain ask174 runs | Resend · 56then Postmark · 41 |
| Procurement and compliance100 runs | Resend · 57then Postmark · 21 |
| Volume and cost at scale40 runs | Postmark · 33then SendGrid · 3 |
| Self-hosting, privacy or residency37 runs | Azure Communication Services · 17then Amazon SES · 16 |
A case is one codebase with one agent, asked several times in different words and as different people. 22 of 45 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 5 coding agents (Codex, Cursor, Claude Code, Muse Code (Muse Spark 1.3), Grok Build CLI (Grok 4.7)) 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 351 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 15 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 MarkdownOther sectors
- Agent sandboxes
- Observability
- AI SRE
- Payments
- Deploy
- Auth
- Product analytics
- Databases
- File storage
- LLM evals & observability
- Voice Agents
- Serverless functions
- Cloud
- AI gateway
- Bot protection
- Search
- Agent frameworks
- Performance in CI
- Document processing & OCR
- Usage-based billing
- Internationalization
- Security testing
- Maps
- Message queues
- AI search
- Code review
- E-signature
- Security platforms
- In-app chat & calls
- Vector search