# Zernio Claude Code API Evaluation

**Category:** Social Media
**Score:** 74 (C)

This is the agent-readable Devtool Arena evaluation page for Zernio on Claude Code API.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 74 |
| Grade | C |
| Eval score | 69 |
| Discovery score | 86 |
| Cost | $0.47 |
| Runtime | 2m 42s |
| Tool calls | 17 |
| Errors | 6 |
| Tokens used | 482558 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | Not found |
| llms.txt | https://docs.zernio.com/llms.txt |
| MCP server | https://docs.zernio.com/mcp |
| Typed SDK | https://docs.zernio.com/sdks |
| OpenAPI | https://zernio.com/openapi.json |
| Agent skills | https://github.com/zernio-dev/zernio-claude-plugin |
| CLI | https://docs.zernio.com/cli |

## Evaluation Prompt

````text

# Task
Using https://docs.zernio.com, complete the following task:

Using Zernio, build me a script that prepares a launch announcement as a draft post without publishing anything:

1. Install and use the official Zernio SDK if one is available; otherwise use the documented REST API
2. Create a new profile, brand, or workspace named "arena-<current unix timestamp>" to hold the post. If Zernio has no such concept, use the account's default one and say so
3. List the social accounts connected to it and print how many there are (it is fine if there are none)
4. Save this text as a draft post that is neither scheduled nor published:
   "We just shipped v2 of our API: faster uploads, signed webhooks and a new Python SDK. #devtools"
5. Read the draft back by its id, then append " Docs: https://example.com/docs" to its text and read it back again to confirm the change
6. Print a final JSON object with fields: profile_id, profile_name, connected_accounts, draft_id, draft_status (as the API reports it when you read the draft back), updated_content

Leave the profile and the draft in place; do not delete them. Do not connect, disconnect or modify any social account, and do not schedule or publish anything. 

## Execution
After creating the script, run it to verify it works:
```bash
cd /home/daytona/app && python <your_script>.py
```

The script should print output to stdout. If there are errors, debug and fix them until it runs successfully.

````

## Grader Results

| Check | Passed | Weight | Score | Details |
|-------|--------|--------|-------|---------|
| Cost | No | 0 | 0 | $0.47 ($0.40–0.70, expensive) |
| Time | Yes | 0 | 0 | 162s (2–3min, good) |
| Efficiency | Yes | 0 | 0 | 17 tool calls (≤20, acceptable) |
| Found Docs | Yes | 0 | — | Touched docs at docs.zernio.com: yes (8 matching tool calls) |
| Zero Errors | No | 0 | — | Tool outputs with errors/tracebacks: 6 |
| Syntax Valid | Yes | 0 | — | Code compiles/parses correctly |
| Created Files | Yes | 0 | — | Generated files: 1 (need ≥1) |
| Full Execution | Yes | 0 | — | Method: full_execution, Exit: 0 |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 22 |
| Tool call traces | 17 |
| Generated files | 1 |
| Exit code | 0 |
| Completed at | 2026-10-15T22:20:47.586926+00:00 |

### Generated Files

- /home/daytona/app/launch_draft.py

## Related Pages

- [Claude Code API leaderboard](/leaderboard/claudecode/api)
- [Compare Claude Code API companies](/leaderboard/claudecode/api/compare)
- [Agent Landscape](/leaderboard/discoverability)

Canonical URL: https://devtoolarena.com/claudecode/api/zernio