PDB-Wild - Edit Precision: leaderboard

The Precise Debugging Benchmark (PDB, 2026) turns coding datasets into debugging tasks with verified injected bugs and checks whether a model fixes them with minimal targeted edits instead of regenerating the program. This board is edit-level precision in percent on PDB-Wild, which has multi-line and repository-level bugs; higher is better.

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 February 2027. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3.1 Pro (Preview)77.8#99
2Claude Opus 4.777.8#85
3Claude Sonnet 4.5Thinking68.7#261
4GPT-5.560.9#54
5Gemini 2.5 Pro58.3#276
6Qwen 3.6 Plus50.5#238
7Kimi K2.645.7#192
8GPT-5.1 Codex37.1#295

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=pdb-wild-edit-precision · How It Works · Data refreshed daily, snapshot 2026-11-21.