(1)
DeepSeek-V3.2 boosts efficiency and reasoning with DSA, scalable RL, agentic data—IMO/IOI wins.
10m
50K+
11
Granite-4.0-h-nano: lightweight instruct model trained via SFT, RL, and merging on diverse data.
11m
10K+
1
Granite-4.0-nano: lightweight instruct model trained via SFT, RL, and merging on diverse data.
11m
10K+
Gemma-3-4B-T1-it is a Taiwan-localized AI optimized for Traditional Chinese.
8m
9.6K
1
A Taiwan-localized reasoning AI optimized for Traditional Chinese.
8m
2.4K
1