Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
Open paper
Benchmark
Model
Rank
Results
mathematical-reasoning-on-aime-2025
Ring-2.5-1T-Zero (High)
–
Accuracy: 91.0
mathematical-reasoning-on-aime24
Ring-2.5-1T-Zero (High)
–
Acc: 93.2
Rank counts only results with a code link.