Comp Engineering Benchmarks

Comp AI · GitHub · Updated July 28, 2026

Comp delivery benchmarks are based on 111 merged pull requests in the last 30 days (655 all-time), with 0.4 hours median cycle time, 0.1 hours median review time, and 3 active contributors. AI-related signals appear on 96.4% of recent work. PR volume is down -31% compared to the prior period.

Median Cycle Time
0.4h
PR open to merge
Median Review Time
0.1h
first review to approval
AI-Related Signals
96.4%
directional signal across recent PRs
Best Signal Fast Delivery
25m
Median cycle time of 25m
Watch Out Declining Cadence
-31%
PR volume down 31% vs prior period

Repo vs Comp AI Average

+12.5pp
AI Signals
+0.2h
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.

Cycle Time by AI-Related Signals

4.6h
with signals
0.7h
baseline
585.1%
difference

PR Breakdown

109 with signals / 112 total PRs

Top AI Tools

cubic 161
claude 62
claude_code 2
ai_generic 1

PR Type Breakdown

bugfix 52
feature 25
unknown 23
chore 4
refactor 3
ci 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