# Superserve Claude Code API Evaluation

**Category:** Sandboxes
**Score:** 86 (B)

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

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 86 |
| Grade | B |
| Eval score | 81 |
| Discovery score | 100 |
| Cost | $0.13 |
| Runtime | 1m 30s |
| Tool calls | 9 |
| Errors | 3 |
| Tokens used | 245657 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | https://context7.com/superserve-ai/superserve |
| llms.txt | https://docs.superserve.ai/llms.txt |
| MCP server | https://docs.superserve.ai/integrations/mcp |
| Typed SDK | https://github.com/superserve-ai/superserve/tree/main/packages/sdk |
| OpenAPI | https://raw.githubusercontent.com/superserve-ai/sandbox/refs/heads/main/api/openapi.yaml |
| Agent skills | https://github.com/superserve-ai/superserve/blob/main/CLAUDE.md |
| CLI | https://github.com/superserve-ai/superserve/tree/main/packages/cli |

## Evaluation Prompt

````text

# Task
Using https://docs.superserve.ai/quickstart, complete the following task:

Using Superserve, build me a script that runs a multi-step computation inside a Superserve sandbox:
        
1. Use the Superserve Python SDK to create/connect to a sandbox
2. Inside the sandbox, execute the following pipeline:
   a. Install the `sympy` package using pip
   b. Run a Python script that:
      - Computes the 10th Fibonacci number iteratively
      - Uses sympy to check if that number is prime
      - Prints the result as JSON: {"fibonacci_10": <number>, "is_prime": <boolean>}
3. Capture the sandbox execution output and print it to stdout

All computation must run inside the Superserve sandbox, not in your local Python process. Do not use subprocess — use the Superserve SDK's execution primitives. 

## 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 | Yes | 0 | 1 | $0.13 ($0.10–0.20, great) |
| Time | Yes | 0 | 1 | 90s (1–2min, great) |
| Efficiency | Yes | 0 | 1 | 9 tool calls (≤10, great) |
| Found Docs | Yes | 0 | — | Touched docs at docs.superserve.ai: yes (2 matching tool calls) |
| Zero Errors | No | 0 | — | Tool outputs with errors/tracebacks: 3 |
| 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 | 12 |
| Tool call traces | 9 |
| Generated files | 1 |
| Exit code | 0 |
| Completed at | 2026-09-23T05:00:27.758449+00:00 |

### Generated Files

- /home/daytona/app/fib_prime.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/superserve