China is doing it again: holy moly! XBAI-o4 Medium: •Parameter: 32,8 B
•Training: Long‑CoT RL + Process Reward Learning (SPRM)
•Benchmarks (High‑Modus):
•AIME24: 86,5
•AIME25: 77,9
•LiveCodeBench v5: 67,2
•C‑EVAL: 89,7
China’s XBAI-o4 Medium Achieves Impressive Benchmark Results
By
–
