# LlamaParse Codex API Evaluation

**Category:** Document Parsing
**Score:** 69 (C)

This is the agent-readable Devtool Arena evaluation page for LlamaParse on Codex API.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 69 |
| Grade | C |
| Eval score | 68 |
| Discovery score | 71 |
| Cost | $0.39 |
| Runtime | 2m 23s |
| Tool calls | 30 |
| Errors | 10 |
| Tokens used | 1251999 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | Not found |
| llms.txt | https://developers.llamaindex.ai/llms.txt |
| MCP server | https://github.com/run-llama/llama-cloud-ts/tree/main/packages/mcp-server |
| Typed SDK | https://pypi.org/project/llama-cloud/ |
| OpenAPI | Not found |
| Agent skills | https://github.com/run-llama/llamaparse-agent-skills |
| CLI | https://github.com/run-llama/llama-parse-cli |

## Evaluation Prompt

````text

# Task
Using https://docs.cloud.llamaindex.ai/llamaparse/getting_started, complete the following task:

Using LlamaParse, build me a script that parses this PDF and extracts structured data: https://www.irs.gov/pub/irs-pdf/fw9.pdf

Print the result as JSON with fields: pages (total count), chunks (array of text blocks), tables (array if any found) 

## 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 | 0 | $0.39 ($0.20–0.40, good) |
| Time | Yes | 0 | 0 | 143s (2–3min, good) |
| Efficiency | No | 0 | 0 | 30 tool calls (>25, inefficient) |
| Found Docs | Yes | 0 | — | Touched docs at docs.cloud.llamaindex.ai: yes (4 matching tool calls) |
| Zero Errors | No | 0 | — | Tool outputs with errors/tracebacks: 10 |
| Syntax Valid | Yes | 0 | — | Code compiles/parses correctly |
| Created Files | Yes | 0 | — | Generated files: 2 (need ≥1) |
| Full Execution | Yes | 0 | — | Manual review override: full execution credit granted (35 points) |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 34 |
| Tool call traces | 30 |
| Generated files | 2 |
| Exit code | 0 |
| Completed at | 2026-09-29T16:45:56.742467+00:00 |

### Generated Files

- /home/daytona/app/parse_w9.py
- /home/daytona/app/requirements.txt

## Related Pages

- [Codex API leaderboard](/leaderboard/codex/api)
- [Compare Codex API companies](/leaderboard/codex/api/compare)
- [Agent Landscape](/leaderboard/discoverability)

Canonical URL: https://devtoolarena.com/codex/api/llamaparse