ModelScope(@ModelScope2022):New open-source SOTA on agentic coding! 🚀 Ornith-1.0-397B achieves 82.4 on SWE-bench Verified and 77.5 on Terminal-Bench 2.1, topping every open model in its class and beating Claude Opus 4.7 on both. 🤖 https://t.co/C18SvXPPDn 📦 Four sizes (9B to 397B-MoE), post-trained on Gemma 4 / Qwen 3.5, MIT licensed and globally accessible. ✨ Notably, Ornith uses RL to generate not just solution rollouts but also the scaffold that drives them. By jointly optimizing both, the model discovers better search trajectories and produces higher-quality solutions. ⚙️ Deployable on a single 8×80GB node, with vLLM and SGLang recipes in the model card.

ModelScope@ModelScope2022

2026.06.26 06:44

New open-source SOTA on agentic coding! 🚀 Ornith-1.0-397B achieves 82.4 on SWE-bench Verified and 77.5 on Terminal-Bench 2.1, topping every open model in its class and beating Claude Opus 4.7 on both. 🤖 📦 Four sizes (9B to 397B-MoE), post-trained on Gemma 4 / Qwen 3.5, MIT licensed and globally accessible. ✨ Notably, Ornith uses RL to generate not just solution rollouts but also the scaffold that drives them. By jointly optimizing both, the model discovers better search trajectories and produces higher-quality solutions. ⚙️ Deployable on a single 8×80GB node, with vLLM and SGLang recipes in the model card.