# Tavus Claude Code API Evaluation

**Category:** Video Agent
**Score:** 74 (C)

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

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 74 |
| Grade | C |
| Eval score | 70 |
| Discovery score | 86 |
| Cost | $0.25 |
| Runtime | 4m 19s |
| Tool calls | 14 |
| Errors | 1 |
| Tokens used | 242424 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | Not found |
| llms.txt | https://tavus.io/llms.txt |
| MCP server | https://docs.tavus.io/sections/agent-tools/mcp-server.md |
| Typed SDK | https://docs.tavus.io/sections/conversational-video-interface/component-library/overview.md |
| OpenAPI | https://docs.tavus.io/openapi.yaml |
| Agent skills | https://github.com/Tavus-Engineering/tavus-skills |
| CLI | https://docs.tavus.io/sections/agent-tools/cli.md |

## Evaluation Prompt

````text

# Task
Using https://docs.tavus.io/api-reference, complete the following task:

Using Tavus, build me a script that generates an AI avatar video:

1. List available avatars/replicas and voices (or use a stock/default avatar if available)
2. Create a video with the avatar speaking: "Hello! This is a ***** video from the Lightsage API leaderboard."
3. Poll for completion if the API is async (check status until the video is ready)
4. Print the result as JSON with fields: video_id, status, video_url (the URL where the video can be viewed or downloaded)

Note: Most video avatar APIs are async — you may need to poll the status endpoint until the video is ready. 

## 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 | $0.25 ($0.20–0.40, good) |
| Time | No | 0 | 0 | 259s (3–5min, slow) |
| Efficiency | Yes | 0 | 0 | 14 tool calls (≤15, good) |
| Found Docs | Yes | 0 | — | Touched docs at docs.tavus.io: yes (9 matching tool calls) |
| Zero Errors | No | 0 | — | Tool outputs with errors/tracebacks: 1 |
| 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 | 17 |
| Tool call traces | 14 |
| Generated files | 1 |
| Exit code | 0 |
| Completed at | 2026-09-23T05:00:29.196576+00:00 |

### Generated Files

- /home/daytona/app/tavus_video.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/tavus