I created a brand new programming language to test LLM models on[2]. It looks like Mistral Large 4 fares about as well as Kimi K3 and Claude Sonnet 5.5[1]. Though it is much slower than Sonnet 5.5 and more expensive than both of those.
1 - https://bench.killswitch-lang.org
2 - https://killswitch-lang.org