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
45.5%
Merged agent PRs in significant repos.
No human reviewer
54.5%
The same significant-repo sample.
Sample
268
Significant-repo PRs behind the market rate.
Agent-Level Autonomy
Window: 2026-07-16 to 2026-08-14. 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 | 79.5% | 66.7% | 25 min | 20.8% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| Cursor | 70.7% | 40% | 47 min | 40% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| Claude Code | 44.4% | 31.7% | 20 min | 47.5% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| Amazon Q Developer | 41.7% | 35% | 26 min | 29.2% | 120 PRs, 120 reposexpanded 365-day window120 of 120 enriched | Published from 365-day sample. |
| Devin | 32% | 13.3% | 22 min | 40.8% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| OpenAI Codex | 32% | 20% | 20 min | 62.5% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| ZCode | 13.3% | 14.2% | 13 min | 55.8% | 120 PRs, 68 repos30-day window120 of 120 enriched | Published |
| Jules | n/a | 18.4% | 1.41h | 35.6% | 87 PRs, 43 repos30-day window87 of 87 enriched | Lifecycle fields published. Significant-repo review rate withheld. |
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.