Open-source Ornith-1.5 launches 397B MoE rivaling Claude Opus
ollama · x · 2026-08-20
The Ornith-1.5 series of open-source models is now available on Ollama, featuring 9B Dense, 35B MoE, and 397B MoE sizes. Trained with end-to-end self-improvement strategies, it achieves state-of-the-art performance on benchmarks like Terminal-Bench and SWE-Bench, claiming to rival Claude Opus 4.8 in reasoning, agentic, and coding tasks.
Key features:
- Architecture: Available in 9B, 35B, and 397B variants, all supporting 256K context and vision input.
- Performance: Scored 86 on SWE-Bench Verified, 86.1 on Terminal-Bench 2.1, and 71.2 on Tool Decathlon.
- Technique: Implements a complete self-improvement loop, jointly optimizing task generation, scaffolding, and solution rollouts.
Related event: Ornith-1.5 Release: 397B MoE Self-Improvement Targets Claude Opus(24 posts)→
More from Models
- Meta releases 816B Muse Spark Open, now the top US open-weights model at AA Index 39 — ArtificialAnlys · 2026-10-16
- Nolla Health Post-Trains Nemotron 3.5 VL: Visual Diagnosis Jumps from 35% to 66.8% — LoganGrasby · 2026-10-16
- Dev argues coding models now beat nearly all engineers in every branch of software — zack_overflow · 2026-10-16
- Prediction: Chinese frontier models could match GPT-6 by March 2027 — teortaxesTex · 2026-10-16
- Liquid AI's d1-ultra, #1 on Artificial Analysis Decision Index, lands on Vercel — JosephJacks_ · 2026-10-16
- Weekly AI roundup: Claude Haiku 5.5 cuts prices ~90%, Gemini 4 Argon output jumps to 1M tokens — DeepLearningAI · 2026-10-16