AutonomyPreviewThis index is in active development: we are still adding agents, refining attribution signatures, and verifying data against sources. The date in the header is when key figures were last re-checked. Numbers can move as coverage improves.
Public GitHub can show whether merged agent pull requests had a human reviewer, how long they took to merge, and whether they touched tests. Significant repos are org-owned or have at least 10 stars. Agent-level rates are withheld when the sample is too concentrated. Sparse exact-bot agents can use an expanded window; those rows are not included in the market rate.
Human reviewed
44%
Merged agent PRs in significant repos.
No human reviewer
56%
The same significant-repo sample.
Sample
268
Significant-repo PRs behind the market rate.
Agent-Level Autonomy
Window: 2026-07-30 to 2026-08-28. Published rates require at least 40 capped PRs across 15 repos. Significant-repo review rates require at least 10 significant PRs across 8 significant repos.
| Agent | Significant review | All-repo review | Time to merge | Tests touched | Sample | Status |
|---|---|---|---|---|---|---|
| GitHub Copilot | 80.5% | 64.2% | 33 min | 31.7% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| Cursor | 77.8% | 35.8% | 1.02h | 55.8% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| Devin | 51.6% | 18.3% | 23 min | 45.8% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| Amazon Q Developer | 43.5% | 34.2% | 25 min | 30.8% | 120 PRs, 120 reposexpanded 365-day window120 of 120 enriched | Published from 365-day sample. |
| ZCode | 31.6% | 25% | 20 min | 60.8% | 120 PRs, 78 repos30-day window120 of 120 enriched | Published |
| Claude Code | 30.5% | 20% | 38 min | 47.5% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| OpenAI Codex | 28.6% | 19.2% | 8 min | 69.2% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| Jules | 12.5% | 22.5% | 57 min | 25% | 120 PRs, 77 repos30-day window120 of 120 enriched | Published |
Read This With the Ranking
Output volume counts what an agent leaves visible. Autonomy adds the lifecycle read: whether merged work had a human reviewer, how quickly it merged, and whether tests changed. For capture details and visibility limits, see the methodology.