Ai Engineering Benchmarks

Vercel · GitHub · Updated September 11, 2026

Ai delivery benchmarks are based on 612 merged pull requests in the last 30 days (2,727 all-time), with 1.3 hours median cycle time, 0.8 hours median review time, and 31 active contributors. AI-related signals appear on 8.7% of recent work. PR volume is up 36% compared to the prior period.

Median Cycle Time
1.3h
PR open to merge
Median Review Time
0.8h
first review to approval
AI-Related Signals
8.7%
directional signal across recent PRs
Best Signal Fast Delivery
1.3h
Median cycle time of 1.3h

Repo vs Vercel Average

+0.8pp
AI Signals
-5.3h
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.

AI Signals vs Cycle Time

Correlation

moderate positive
r = 0.41 (14 weeks)

Cycle Time by AI-Related Signals

27.5h
with signals
16.2h
baseline
69.5%
difference

PR Breakdown

45 with signals / 637 total PRs

Top AI Tools

claude_code 35
chatgpt 19
claude 12
copilot 3

PR Type Breakdown

unknown 388
bugfix 133
feature 56
chore 18
ci 9
refactor 4

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 8 hours, 4 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