Ai Engineering Benchmarks

Vercel · GitHub · Updated June 3, 2026

Ai delivery benchmarks are based on 271 merged pull requests in the last 30 days (1,221 all-time), with 0.9 hours median cycle time, 0.7 hours median review time, and 34 active contributors. AI-related signals appear on 6.3% of recent work. PR volume is up 42% 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
6.3%
directional signal across recent PRs
Best Signal Fast Delivery
55m
Median cycle time of 55m

Repo vs Vercel Average

-1.2pp
AI Signals
-7.2h
Cycle Time
-0.1h
Review Time

Delivery Trend and AI Signals

PR Backlog (Humans)

Excludes AI agents and automation accounts.

PR Backlog (AI Agents)

AI coding agents only.

Top AI Coding Agents

Most active AI coding agents in the last 90 days.

AI Signals vs Cycle Time

Correlation

moderate positive
r = 0.40 (14 weeks)

Cycle Time by AI-Related Signals

17.7h
with signals
22.4h
baseline
-21.3%
difference

PR Breakdown

64 with signals / 279 total PRs

Top AI Tools

cursor 42
claude 13
chatgpt 3
copilot 2

PR Type Breakdown

feature 77
bugfix 75
refactor 36
ci 25
docs 20
chore 17

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 16 hours, 27 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