[bubblyworld]

My barely-informed guess is that they don't have the resources to run it (it's a 200b+ model).

[regularfry]

They could compare to DeepSeek-Coder-V2-Lite-Instruct. That's a 16B model, and it comes out at 24.3 on LiveCodeBench. Given the size delta they're respectably close - they're only just behind at 23.4. The full V2 is way ahead.

[smcleod]

That’s for the larger model, most people running it locally use the -lite model (both of which has lots of benchmarks published)