Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
MAP-Neomap-neo.github.io · Low evidenceMAP Neo is a fully open-sourced bilingual large language model with 7 billion parameters, trained from scratch on 4.5 trillion high-quality tokens. It provides all training details, including the cleaned pre-training corpus, data cleaning pipeline, checkpoints, and training framework, to enhance transparency and reproducibility in LLM research.
Parse Score