AI Model2026
A multimodal model for coding, visual understanding, and multi-step tool use, with a 1-million-token context window. Its MoE architecture has 2.8T total parameters and activates 104B per token; weights are open, but local inference demands substantial compute.
AI Dataset2026
Provides scientific-reasoning and tool-use trajectories for training agent foundation models, alongside reinforcement-learning tasks. Its staged data makes the Axion 1.0 training process easier to inspect and reproduce.
AI Model2026
A 65B dense language model trained on 12T text and code tokens for reasoning and agentic coding, with context support up to 1M tokens. Its Terminal-Bench 2.1 result stands out, though benchmark scores depend on evaluation setup.
AI Model2026
A sparse MoE base language model for continued training and research, with 280B total parameters and 14B activated per token. Supports up to a 1M-token context for fine-tuning and inference.