PDB-Wild - Edit Precision: leaderboard
Metric: Edit-level precision (%): share of a model's predicted edits that match an essential ground-truth fix (line tolerance 1), on PDB-Wild multi-line and repository-level bugs; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 77.8 |
| 2 | Claude Opus 4.7 | 77.8 |
| 3 | Claude Sonnet 4.5 (Thinking) | 68.7 |
| 4 | GPT-5.5 | 60.9 |
| 5 | Gemini 2.5 Pro | 58.3 |
| 6 | Qwen 3.6 Plus | 50.5 |
| 7 | Kimi K2.6 | 45.7 |
| 8 | GPT-5.1 Codex | 37.1 |
Interactive version: theaggregate.ai/benchmark?slug=pdb-wild-edit-precision · How It Works · Data refreshed daily, snapshot 2026-10-07.