Extremely hard, multi-turn, open-source-grounded coding evaluations that reliably break every current frontier models (Claude, GPT, Grok, Gemini, Llama, etc.) on numerical stability, zero-allocation, ...
Note: This project accompanies dilithium-py which is a pure-python implementation of ML-DSA and CRYSTALS-Dilithium and shares a lot of the lower-level code of this implementation. kyber-py has been ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback