Anthropic Cookbook Engineering Benchmarks

Anthropic · GitHub · Updated September 11, 2026

Anthropic Cookbook delivery benchmarks are based on 8 merged pull requests in the last 30 days (103 all-time), with 0.2 hours median cycle time, 0.1 hours median review time, and 3 active contributors. AI-related signals appear on 12.5% of recent work. PR volume is up 60% compared to the prior period.

Median Cycle Time
0.2h
PR open to merge
Median Review Time
0.1h
first review to approval
AI-Related Signals
12.5%
directional signal across recent PRs
Best Signal Fast Delivery
13m
Median cycle time of 13m

Repo vs Anthropic Average

-5.2pp
AI Signals
-1.2h
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.

AI Signals vs Cycle Time

Correlation

moderate positive
r = 0.39 (8 weeks)

Cycle Time by AI-Related Signals

1.6h
with signals
20.8h
baseline
-92.5%
difference

PR Breakdown

1 with signals / 9 total PRs

Top AI Tools

claude 1

PR Type Breakdown

docs 3
bugfix 3
feature 2

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 9 hours, 47 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