SecRepoBench (Aider) - Pass@1: leaderboard
Metric: Completions that pass the unit tests, pass@1 (%). Source: secrepobench.github.io. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 70.1 |
| 2 | GPT-5 | 69.5 |
| 3 | Claude Sonnet 4 (Thinking) | 64.8 |
| 4 | O3 | 60.7 |
| 5 | GPT-4.1 | 59.1 |
| 6 | O4 Mini | 58.2 |
| 7 | Claude Sonnet 4.5 (Thinking) | 56.6 |
Interactive version: theaggregate.ai/benchmark?slug=secrepobench-aider-pass-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.