# Bolna Gemini API Evaluation

**Category:** Voice Telephony
**Score:** 71 (C)

This is the agent-readable Devtool Arena evaluation page for Bolna on Gemini API.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 71 |
| Grade | C |
| Eval score | 72 |
| Discovery score | 71 |
| Cost | $0.23 |
| Runtime | 4m 36s |
| Tool calls | 22 |
| Errors | 0 |
| Tokens used | 395095 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | Not found |
| llms.txt | https://www.bolna.ai/docs/llms.txt |
| MCP server | https://www.bolna.ai/docs/mcp-server |
| Typed SDK | https://github.com/bolna-ai/web-call |
| OpenAPI | Not found |
| Agent skills | https://github.com/bolna-ai/skills |
| CLI | https://github.com/bolna-ai/cli |

## Evaluation Prompt

````text

# Task
Using https://www.bolna.ai/docs, complete the following task:

Using the Bolna REST API, build me a script that creates a voice AI agent:

1. Use the Bolna REST API (no SDK - use the requests library)
2. Create a simple voice AI agent with a greeting message
3. List available agents to confirm creation
4. Print the result as JSON with fields: agent_id, agent_name, created

Use HTTP requests to call the Bolna API. 

## 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 | $0.23 ($0.20–0.40, good) |
| Time | No | 0 | 0 | 276s (3–5min, slow) |
| Efficiency | Yes | 0 | 0 | 22 tool calls (≤25, below average) |
| Found Docs | Yes | 0 | — | Touched docs at bolna.ai: yes (10 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: 1 (need ≥1) |
| Full Execution | Yes | 0 | — | Method: full_execution, Exit: 0 |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 23 |
| Tool call traces | 22 |
| Generated files | 1 |
| Exit code | 0 |
| Completed at | 2026-10-16T00:06:31.229295+00:00 |

### Generated Files

- /home/daytona/app/create_agent.py

## Related Pages

- [Gemini API leaderboard](/leaderboard/gemini/api)
- [Compare Gemini API companies](/leaderboard/gemini/api/compare)
- [Agent Landscape](/leaderboard/discoverability)

Canonical URL: https://devtoolarena.com/gemini/api/bolna