PostcondBench - Correctness: leaderboard
Metric: Corr@1 times 100 (%): expected share of methods whose generated postcondition set passes every test, one sampled postcondition set per method (k = 1, five samples drawn), averaged over the Python and Java splits (210 repository methods each) and three input settings (code only, comments only, code plus comments); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 62.9 |
| 2 | GPT-5 | 48.3 |
| 3 | Llama 4 Maverick | 21.4 |
| 4 | Qwen 3 32B | 11.8 |
| 5 | Gemma 3 27B | 11 |
Interactive version: theaggregate.ai/benchmark?slug=postcondbench-correctness · How It Works · Data refreshed daily, snapshot 2026-10-07.