1
MaxxBench – "Nice DeepSWE score. But is it true?"
How coding models respond when familiar engineering tasks ask for something different.
MaxxBench Blog
Evaluating whether frontier coding agents possess generalized intelligence by evolving software requirements.
- Popular posts
- 1
- Total points
- 356
- HN comments
- 100
- Rank
- #3,754 company
Visit maxxbench.unlap.ai → On Hacker News Nov 2026 – Nov 2026