Ornith-1.0 Open-Source Coding Models Released
s_mohinii · x · 2026-07-13
- The open-source code model family Ornith-1.0 has been released, targeting agentic coding scenarios.
- It comes in various sizes: 9B Dense, 31B Dense, 35B MoE, and 397B MoE.
- The team claims it sets new highs on coding benchmarks among open-source models of similar scale, including:
- Terminal-Bench 2.1: 77.5
- SWE-Bench: verified 82.4, pro 62.2, Multilingual 78.9
- NL2Repo: 48.2
- SWE Atlas: QnA 41.2, RF 42.6, TW 39.1
- ClawEval: 77.1
- The models are continually trained based on gemma4 and qwen3.5, utilizing a self-improvement training strategy: they use reinforcement learning not only to generate problem-solving trajectories but also to create specific scaffolds that drive tasks.
More from coding & agent
- Hermes Agent rewrite proposal applies RIA and Logic Bus rules — Promptmethus · 2026-07-22
- Devin adds e2b sandboxes for remote agent execution — badphilosopher · 2026-07-22
- Hermes Agent Refactoring Proposal: Decoupling via Event Bus and Monorepo Slicing — Promptmethus · 2026-07-22
- ty now reads Pydantic config keywords and field metadata — charliermarsh · 2026-07-22
- Pensar Launches AI Security Agent to Autonomously Discover and Patch 0-Days — andriy_mulyar · 2026-07-22
- ty adds first-class Pydantic support, including strict and lax field handling — charliermarsh · 2026-07-22