# Ornith-1.0

DeepReinforce, released 2026-06-25

**Verdict: conditional.** A strong MIT-licensed open-source agentic coding model family that achieves frontier-competitive benchmarks — beating Claude Opus 4.7 on both Terminal-Bench 2.1 and SWE-Bench Verified — but requires self-hosting with significant GPU resources and comes from a new lab with limited track record. Last verified 2026-06-30.

## Pricing

- Input: Free (MIT license)
- Output: Free (MIT license)
- Context: 256K tokens

## Strengths

- Agentic coding with multi-step tool calling — outperforms Claude Opus 4.7 on Terminal-Bench 2.1 (77.5 vs 70.3) and SWE-Bench Verified (82.4 vs 80.8)
- Self-hosted coding agents with full data privacy — MIT license, no API dependency, runs on your own infrastructure
- Edge deployment with the 9B variant — matches or exceeds Gemma 4-31B on SWE-Bench Verified (69.4 vs 52) while fitting on a single consumer GPU
- Self-scaffolding RL training produces per-task strategies that outperform fixed human-designed harnesses on agentic coding benchmarks
- Teams without GPU infrastructure — no managed API from DeepReinforce; you must provision and maintain your own inference servers
- General-purpose chat or non-coding tasks — heavily specialized for agentic coding harnesses; not benchmarked or tuned for conversation, writing, or multimodal use
- Production deployment with reliability SLAs — from a new lab with no managed service, limited community adoption data, and unverified benchmark claims

## Benchmarks

- SWE-Bench Verified: 82.4 (https://deep-reinforce.com/ornith_1_0.html)
- Terminal-Bench 2.1 (Terminus-2): 77.5 (https://deep-reinforce.com/ornith_1_0.html)
- SWE-Bench Pro: 62.2 (https://deep-reinforce.com/ornith_1_0.html)
- SWE-Bench Multilingual: 78.9 (https://deep-reinforce.com/ornith_1_0.html)

## Sources

- [Hugging Face: deepreinforce-ai/Ornith-1.0-397B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B)
- [Hugging Face — Ornith-1.0-9B Model Card](https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B)
- [MarkTechPost — DeepReinforce Releases Ornith-1.0](https://www.marktechpost.com/2026/06/25/deepreinforce-releases-ornith-1-0-an-open-source-coding-model-family-that-learns-its-own-rl-scaffolds/)
- [GitHub — Ornith-1 Repository](https://github.com/deepreinforce-ai/Ornith-1)
- [LLM Reference — Ornith 1.0](https://www.llmreference.com/model-family/ornith-1.0)
- [DeepReinforce Official Announcement](https://deep-reinforce.com/ornith_1_0.html)
- [TechTimes — Open-Source Coding Model Ornith-1.0 Writes Its Own Training Scaffold](https://www.techtimes.com/articles/319122/20260626/open-source-coding-model-ornith-10-writes-its-own-training-scaffold-reinforcement-learning.htm)
- [Simon Willison — Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding](https://simonwillison.net/2026/Jun/29/ornith/)

Canonical: https://neomanex.com/models/ornith-1-0