Skip to main content
Search

MiniMax

1 related articles

Subscribe to updates
  1. arXiv

    MiniMax-M2.7 activates about 9.8B parameters per token and scores 56.2 on SWE-bench Pro

    MiniMax released the M2 series of Mixture-of-Experts language models, with the flagship M2 holding 229.9B total parameters while activating only 9.8B per token; the latest checkpoint, M2.7, scores 56.2 on SWE-bench Pro, in the same band as Claude Opus 4.6 at 57.3 and GPT 5.4 at 57.7. Most of the series' capability comes from agent-native post-training: data pipelines grounded in executable workspaces and artifact-aligned rewards, plus a reinforcement-learning system called Forge. M2.7 also shows an early form of self-evolution, autonomously triaging failed training runs and editing its own scaffold.

You’re all caught up