Polar Engineering Benchmarks

Polar.sh · GitHub · Updated September 11, 2026

Polar delivery benchmarks are based on 395 merged pull requests in the last 30 days (4,196 all-time), with 1.4 hours median cycle time, 0.1 hours median review time, and 12 active contributors. AI-related signals appear on 88.6% of recent work. PR volume is up 14% compared to the prior period.

polar merged 272 PRs in the past 30 days with 20.96% showing AI-related signals. Median cycle time is 0.22 hours.
Median Cycle Time
1.4h
PR open to merge
Median Review Time
0.1h
first review to approval
AI-Related Signals
88.6%
directional signal across recent PRs
Best Signal Fast Delivery
1.4h
Median cycle time of 1.4h

Repo vs Polar.sh Average

+44.3pp
AI Signals
+0.8h
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.

Top AI Coding Agents

Most active AI coding agents in the last 90 days.

AI Signals vs Cycle Time

Correlation

strong negative
r = -0.61 (14 weeks)

Cycle Time by AI-Related Signals

22.7h
with signals
13.8h
baseline
64.8%
difference

PR Breakdown

395 with signals / 417 total PRs

Top AI Tools

cubic 468
claude 24
cursor 24
claude_code 14
copilot 10

PR Type Breakdown

unknown 198
bugfix 82
feature 70
refactor 15
chore 10
docs 10

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 2 hours, 3 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