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
50.8%
Merged agent PRs in significant repos.
No human reviewer
49.2%
The same significant-repo sample.
Sample
252
Significant-repo PRs behind the market rate.
Agent-Level Autonomy
Window: 2026-06-25 to 2026-07-24. 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 | 75% | 68.3% | 38 min | 26.7% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| Cursor | 62.8% | 35.8% | 28 min | 45% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| OpenAI Codex | 56.5% | 36.7% | 35 min | 66.7% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| Claude Code | 51.4% | 26.7% | 11 min | 45% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| Devin | 42.1% | 15.8% | 14 min | 23.3% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| Amazon Q Developer | 37% | 36.7% | 27 min | 30% | 120 PRs, 120 reposexpanded 365-day window120 of 120 enriched | Published from 365-day sample. |
| Jules | 26.1% | 19.2% | 1.4h | 17.5% | 120 PRs, 120 repos30-day window120 of 120 enriched | Published |
| ZCode | 23.8% | 25% | 23 min | 48.2% | 112 PRs, 63 repos30-day window112 of 112 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.