Ai Engineering Benchmarks

Vercel · GitHub · Updated July 28, 2026

Ai delivery benchmarks are based on 409 merged pull requests in the last 30 days (1,878 all-time), with 0.9 hours median cycle time, 0.7 hours median review time, and 29 active contributors. AI-related signals appear on 14.7% of recent work. PR volume is up 56% compared to the prior period.

Median Cycle Time
0.9h
PR open to merge
Median Review Time
0.7h
first review to approval
AI-Related Signals
14.7%
directional signal across recent PRs
Best Signal Fast Delivery
52m
Median cycle time of 52m

Repo vs Vercel Average

+6.7pp
AI Signals
-6.6h
Cycle Time
-0.2h
Review Time

Delivery Trend and AI Signals

PR Backlog (Humans)

Excludes AI agents and automation accounts.

PR Backlog (AI Agents)

AI coding agents only.

Cycle Time by AI-Related Signals

32.8h
with signals
18.1h
baseline
81.3%
difference

PR Breakdown

91 with signals / 419 total PRs

Top AI Tools

claude 55
claude_code 24
chatgpt 13
cursor 3

PR Type Breakdown

unknown 165
bugfix 130
feature 56
docs 31
chore 19
refactor 3

Methodology

Metrics are computed from merged pull request data synced daily from GitHub. AI-related metrics are directional signals inferred from pull request activity patterns and heuristics. Summary metrics use a 30-day rolling window; trends use a 90-day window. Last updated 28 minutes ago.

Updated daily from public GitHub pull requests.

See Your Team's Benchmarks

Get this analytics stack for your team

Connect GitHub and see cycle time, review bottlenecks, PR flow, and trend changes in minutes.

Connect Repos