# LanceDB Claude Code API Evaluation

**Category:** Vector Databases
**Score:** 72 (C)

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

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 72 |
| Grade | C |
| Eval score | 67 |
| Discovery score | 86 |
| Cost | $0.44 |
| Runtime | 4m 32s |
| Tool calls | 16 |
| Errors | 2 |
| Tokens used | 353050 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | https://context7.com/lancedb/lancedb |
| llms.txt | https://docs.lancedb.com/llms.txt |
| MCP server | https://github.com/lancedb/lancedb-mcp-server |
| Typed SDK | https://github.com/lancedb/lancedb/blob/main/python/python/lancedb/py.typed |
| OpenAPI | https://docs.lancedb.com/api-reference/openapi.json |
| Agent skills | https://github.com/lancedb/lancedb/blob/main/nodejs/AGENTS.md |
| CLI | Not found |

## Evaluation Prompt

````text

# Task
Using https://lancedb.github.io/lancedb, complete the following task:

Using LanceDB, build me a FAQ search system:

1. Store these 3 FAQs:
   - Q: "How do I reset my password?" A: "Go to Settings > Security > Reset Password"
   - Q: "How do I cancel my subscription?" A: "Go to Settings > Billing > Cancel Plan"
   - Q: "How do I update my email?" A: "Go to Settings > Profile > Edit Email"

2. Search for: "I can't log into my account"

3. Print the best matching FAQ and its similarity score 

## 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 | $0.44 ($0.40–0.70, expensive) |
| Time | No | 0 | 0 | 272s (3–5min, slow) |
| Efficiency | Yes | 0 | 0 | 16 tool calls (≤20, acceptable) |
| Found Docs | Yes | 0 | — | Touched docs at lancedb.github.io: yes (3 matching tool calls) |
| Zero Errors | No | 0 | — | Tool outputs with errors/tracebacks: 2 |
| 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 | 18 |
| Tool call traces | 16 |
| Generated files | 1 |
| Exit code | 0 |
| Completed at | 2026-09-23T04:16:32.379841+00:00 |

### Generated Files

- /home/daytona/app/faq_search.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/lancedb