AI Code Review Accuracy (2026): We Seeded 9 Defects — What Four Reviewers Found, Missed, and Made Up

AI Coding2026-07-11YixScout editorial teamLast reviewed: 2026-07-11 by YixScout editorial team
10 min readReviewed

We currently publish two completed local CLI results, not a league table. On the fixed nine-defect PR, Claude Code found 8/9 and GitHub Copilot CLI found 5/9. Each response contained one finding adjudicated as false positive against the fixture ledger.

Quick answer: accuracy has at least two dimensions — seeded-defect recall and adjudicated false positives. Both must be checked against code before a team turns an AI finding into a change.

Completed results on the fixed fixture

Completed reviewerSeeded defects foundAdjudicated false positives
Claude Code 2.1.1178/91
GitHub Copilot CLI 1.0.705/91
One completed run per listed CLI tool, checked 2026-07-11. This is a reproducible fixture observation, not a product ranking.

How to handle a possible false positive

A plausible explanation is not enough. Check the reported line, identify the product behavior it would break, and write a reproducing test before changing code. In both completed runs, the adjudicated false positive was a claim about the fixture's intentional batch-size behavior; the ground-truth ledger explains why it is not a defect.

Scope and limits

Codex CLI and Cursor Agent produced no review output in the read-only non-interactive attempts, so they have no public score here. We did not test PR-integrated SaaS review products, and one run per CLI tool cannot predict production performance. Re-run the protocol on your own repository before using it for procurement or a merge policy.

Sources checked 2026-07-11: fixed seeded-PR fixture, pre-run ground-truth ledger, and two completed run records (Claude Code 2.1.117 and GitHub Copilot CLI 1.0.70). Refresh due 2026-08-09.

Sources and evidence

Sources

  • Claude Code documentation
    Checked 2026-07-11Medium volatility

    Use for Claude Code product positioning only; benchmark results come from the archived run record.

  • GitHub Copilot plans
    Checked 2026-07-11High volatility

    Use for Copilot plan and product context only; benchmark results come from the archived run record.

Evidence

  • BenchmarkChecked 2026-07-11

    Two completed local CLI runs on one fixed nine-defect fixture. This is not a ranking of PR-integrated review products or a general performance claim.

    Methodology
MethodologyRefresh due: 2026-08-09

Related resource guides