Limite 1B-Violetto is Paradigma's 1-billion parameter mathematical reasoning model trained on 300B curated tokens, achieving 74.25% on BeyondAIME by using synthetic data, SFT, and RL post-training. The lightly instruction-tuned model excels at competition-level mathematics but struggles with general instruction-following and scope management.
Limite is a 1-billion parameter language model developed by Paradigma that achieves 94% on AIME and 74.25% on BeyondAIME through efficient training on curated data and mathematical reasoning optimizations. The model is designed for high-throughput mathematical problem-solving with minimal instruction-tuning, though it has limitations in general instruction-following tasks outside mathematics.