RealBench (Holistic) - Level 4: leaderboard
Metric: Test pass rate (%), passed tests over all tests of each task, averaged over the level-4 tasks (10 repositories of about 2,360 lines), with holistic generation (the whole repository in one pass); RealBench repository-level Python code generation from natural-language requirements plus UML package and class diagrams (61 real repositories in four size levels), one greedy solution per task through the official APIs; higher is better. Source: arxiv.org. Saturation forecast: Around May 2028. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4 (20250514) | 14.3 |
| 2 | GPT-4o (2024-05-13) | 13.51 |
| 3 | Gemini 2.5 Flash | 3.07 |
| 4 | DeepSeek V3 | 2.21 |
| 5 | Qwen 3 235B A22B | 0.91 |
| 6 | Qwen 2.5 Coder 7B Instruct | 0.85 |
Interactive version: theaggregate.ai/benchmark?slug=realbench-holistic-level-4 · How It Works · Data refreshed daily, snapshot 2026-10-07.