Comp Engineering Benchmarks

Comp AI · GitHub · Updated June 3, 2026

Comp delivery benchmarks are based on 107 merged pull requests in the last 30 days (404 all-time), with 0.1 hours median cycle time, 0.0 hours median review time, and 4 active contributors. AI-related signals appear on 93.5% of recent work. PR volume is up 37% compared to the prior period.

Median Cycle Time
0.1h
PR open to merge
Median Review Time
0.0h
first review to approval
AI-Related Signals
93.5%
directional signal across recent PRs
Best Signal Fast Delivery
8m
Median cycle time of 8m

Repo vs Comp AI Average

+21.8pp
AI Signals
0.0h
Cycle Time
0.0h
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 negative
r = -0.38 (14 weeks)

Cycle Time by AI-Related Signals

2.3h
with signals
0.3h
baseline
773.1%
difference

PR Breakdown

105 with signals / 107 total PRs

Top AI Tools

cubic 205
claude 105
cursor 5
chatgpt 3
claude_code 2

PR Type Breakdown

bugfix 67
feature 28
chore 5
refactor 4
docs 2
ci 1

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, 25 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