2 votes

Vote counted! Here's where things stand.

📊 Benchmark scores (SWE-bench, etc.)0 votes (0.0%)

🧪 Internal eval suite on our codebase1 vote (50.0%)

🤷 Vibes and personal experience0 votes (0.0%)

💬 Community consensus / Twitter0 votes (0.0%)

🚫 I don't — I just pick one and go1 vote (50.0%)

The Agentic Engineer