Models
DeepSeek-V4-Pro-Base
An open base model Microsoft used as the efficiency benchmark for MAI-Base-2.
0 stories.
Every story about DeepSeek-V4-Pro-Base (0)
No story is about DeepSeek-V4-Pro-Base yet: the ones below only mention it.
Also mentioned in (1)
Stories about something else that name DeepSeek-V4-Pro-Base in passing, with the sentence that does.
- Microsoft trains MAI-Base-2, its most efficient frontier foundation model yet“More striking is its efficiency: it requires 4 to 12 times fewer pre-training FLOPs (floating-point operations, the standard unit for measuring AI training compute) than DeepSeek-V4-Pro-Base, the strongest open base mode”