MiMo-7B-RL, trained from scratch with a reasoning-focused pretraining mix and GRPO on 130K verifiable math and code problems, reports higher benchmark scores than o1-mini on AIME 2025 and LiveCodeBench v5 and v6.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining
MiMo-7B-RL, trained from scratch with a reasoning-focused pretraining mix and GRPO on 130K verifiable math and code problems, reports higher benchmark scores than o1-mini on AIME 2025 and LiveCodeBench v5 and v6.