DeepReinforce AI has released the Ornith-1.0 family of open-source models, designed for agentic coding tasks. The models, available in various sizes including 9B, 35B, and 397B parameters, are built upon Gemma 4 and Qwen 3.5. Ornith-1.0 models have demonstrated state-of-the-art performance on coding benchmarks like Terminal-Bench 2.1 and SWE-Bench, utilizing a self-improving training framework that optimizes both solution generation and the underlying scaffolding. AI
IMPACT These open-source models for agentic coding could accelerate development and adoption of AI-powered coding assistants.
RANK_REASON The cluster contains announcements of new model releases from DeepReinforce AI, including specific model names and parameter counts, along with details on their capabilities and benchmarks.
Read on Hugging Face Trending Models →
- deepreinforce-ai/Ornith-1.0-35B
- deepreinforce-ai/Ornith-1.0-35B-GGUF
- deepreinforce-ai/Ornith-1.0-397B
- deepreinforce-ai/Ornith-1.0-9B
- deepreinforce-ai/Ornith-1.0-9B-GGUF
- Docker
- Gemma 4
- Hugging Face
- llama.cpp
- llama-cpp-python
- Qwen 3.5
- SGLang
- SWE-Bench
- Terminal-Bench 2.1
- transformers
- vLLM
AI-generated summary · Google Gemini · from 5 sources. How we write summaries →
