Deepseek V4 Pro 0813 is the most unreliable model I have tried, it works on pass@3 shockingly well you can get it to match Sol or Fable perhaps in task done, but it's horrendous at pass@1 very prone to going wrong and doing horribly at most benches.
I am not sure what it is buy I suspect it might be GRPO.
I am not sure what it is buy I suspect it might be GRPO.