Anthropic Sdk Python Engineering Benchmarks
Anthropic Sdk Python delivery benchmarks are based on 1 merged pull requests in the last 30 days (18 all-time), with 61.2 hours median cycle time, 60.9 hours median review time, and 1 active contributors. AI-related signals appear on 0.0% of recent work.
Median Cycle Time
61.2h
PR open to merge
Median Review Time
60.9h
first review to approval
AI-Related Signals
0.0%
directional signal across recent PRs
Watch Out
Review Pressure
60.9h
Median review time is 60.9h
Repo vs Anthropic Average
-22.0pp
AI Signals
+58.4h
Cycle Time
+60.8h
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
184.4h
with signals
61.2h
baseline
201.5%
difference
PR Breakdown
1 with signals /
2 total PRs
Recent Pull Requests
View PR Explorer| Title | Author | AI |
|---|---|---|
| chore(examples): bump tools_runner.py to claude-sonnet-4-5-… | GopalGB | AI |
| chore(examples): update shebang from poetry to uv | xodn348 | — |
| fix(transform schema): support enums | RobertCraigie | — |
| fix(client): AsyncAnthropic._make_status_error missing 529 … | stephen | — |
| fix(tools): use filtered messages list in async compaction | fede-kamel | — |
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 17 hours, 55 minutes ago.
Updated daily from public GitHub pull requests.
See Your Team's Benchmarks