Model Releases
Ornith-1.5: The Dawn of Self-Improving Intelligence 35B-A3B is Here
Deep Reinforce AI releases the milestone Ornith-1.5 family, featuring a 397B MoE, 35B MoE, and 9B Dense models that rivals Claude Opus 4.8 through revolutionary end-to-end self-improvement.
August 20, 2026
Model ReleaseOrnith-1.5
Introduction: A Paradigm Shift in Open Source
On August 20, 2026, the landscape of open-source artificial intelligence shifted fundamentally. Deep Reinforce AI has officially released the Ornith-1.5 model family, a collection of LLMs that represents more than just a marginal improvement in parameter count. This release marks a historical milestone where open-source models are no longer just chasing proprietary giants—they are setting new benchmarks for autonomous intelligence.
At the heart of this release is the Ornith-1.5-35B-A3B, a Mixture-of-Experts (MoE) model that defies the traditional scaling laws. While many models struggle to maintain reasoning capabilities as they optimize for efficiency, Ornith-1.5 utilizes a unique self-improvement loop that allows it to bridge the gap between mid-sized models and massive frontier systems. For developers, this means access to 'frontier-class' intelligence on much more accessible hardware.
- Release Date: August 20, 2026
- Significance: First major open-source model to rival Claude Opus 4.8 in reasoning
- Core Innovation: End-to-end self-improving training loop
Architecture: The Power of Self-Scaffolding MoE
The Ornith-1.5 family is designed with scalability in mind, offering a range of architectures to suit different deployment needs. The family includes a 9B Dense model for edge applications, the flagship 35B MoE (A3B) for high-performance reasoning, and a massive 397B MoE variant for ultra-complex enterprise workloads. The 35B variant utilizes an 'Active 3B' architecture, meaning that despite having 35 billion total parameters, only 3 billion are activated per token, ensuring lightning-fast inference speeds.
What truly sets Ornith-1.5 apart is its training methodology. Building upon the self-scaffolding strategies introduced in Ornith-1.0, the 1.5 series implements a complete self-improvement loop. During training, the model does not just consume static datasets; it proposes its own new tasks, generates task-specific scaffolds, and produces solution rollouts for reinforcement learning. This creates a continuous cycle of learning where the model effectively becomes its own teacher.
- Model Family: 9B Dense, 35B MoE (A3B), and 397B MoE
- Architecture: Mixture-of-Experts (MoE) with sparse activation
- Training: End-to-end self-improvement via task generation and RL rollouts
- License: MIT License (Unrestricted commercial and research use)
Benchmarks: Shattering the Ceiling
The performance metrics for the Ornith-1.5-35B-A3B are nothing short of staggering. In coding and software engineering tasks, the model demonstrates a level of autonomy that was previously thought to be the exclusive domain of much larger models. On the SWE-Bench, it achieved a verified score of 86, proving its ability to handle real-world repository-level engineering tasks with high precision.