# Daytona Kilo Code API Evaluation

**Category:** Sandboxes
**Score:** 87 (B)

This is the agent-readable Devtool Arena evaluation page for Daytona on Kilo Code API.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 87 |
| Grade | B |
| Eval score | 82 |
| Discovery score | 100 |
| Cost | $0.07 |
| Runtime | 1m 2s |
| Tool calls | 8 |
| Errors | 0 |
| Tokens used | 226664 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | https://context7.com/daytonaio/daytona |
| llms.txt | https://www.daytona.io/docs/llms.txt |
| MCP server | https://www.daytona.io/docs/en/mcp |
| Typed SDK | https://registry.npmjs.org/@daytona/sdk |
| OpenAPI | https://www.daytona.io/docs/openapi.json |
| Agent skills | https://www.daytona.io/docs/en/agent-skills |
| CLI | https://www.daytona.io/docs/en/tools/cli |

## Evaluation Prompt

````text

# Task
Using https://www.daytona.io/docs/en/python-sdk/, complete the following task:

Using Daytona, build me a script that runs a multi-step computation inside a Daytona sandbox:
        
1. Use the Daytona 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 Daytona sandbox, not in your local Python process. Do not use subprocess — use the Daytona 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 | $0.07 ($0.05–$0.10, great) |
| Time | Yes | 0 | 0 | 62s (60s–90s, good) |
| Efficiency | Yes | 0 | 1 | 8 tool calls (≤10, great) |
| Found Docs | Yes | 0 | — | Touched docs at daytona.io: yes (4 matching tool calls) |
| Zero Errors | Yes | 0 | — | No errors in tool outputs |
| Syntax Valid | Yes | 0 | — | Code compiles/parses correctly |
| Created Files | Yes | 0 | — | Generated files: 2 (need ≥1) |
| Full Execution | Yes | 0 | — | Method: full_execution, Exit: 0 |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 9 |
| Tool call traces | 8 |
| Generated files | 2 |
| Exit code | 0 |
| Completed at | 2026-10-20T18:31:13.43275+00:00 |

### Generated Files

- /home/daytona/app/opencode.json
- /home/daytona/app/run_computation.py

## Related Pages

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

Canonical URL: https://devtoolarena.com/kilo/api/daytona