Benchmarking VS Code with VSC-Bench: How to measure agent performance
Official Schedule Context
- Date/time: 2026-07-01 · 11:40am-12:00pm
- Track/room: Track M · Track M
- Speaker(s): Ross Wollman
- Session type/status: sponsor · confirmed
Official Description
"Agent quality in VS Code depends on a stack of variables: model, version, prompts, extensions, MCP
servers, and more. Each one affects quality, tokens, and latency—and they interact in ways that are
hard to reason about. In this session, we’ll show how to benchmark different configurations using
VSC-Bench so you can compare results side by side and understand what actually works. Instead of
guessing which setup is better, you’ll learn how to measure tradeoffs and make data-driven
decisions."
Related YouTube Video
No related AI Engineer channel video found yet.
Transcript Status
No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.
People
Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.