Ornith-1.5 Launches: 397B Model Matches Claude Opus in Coding Benchmarks
testingcatalog · x · 2026-08-19
DeepReinforce released the Ornith-1.5 family of open models in 397B MoE, 35B MoE, and 9B Dense sizes. The flagship 397B model scores 86.1 on Terminal-Bench 2.1 and 86 on SWE-bench Verified, matching the performance of Claude Opus 4.8. The 35B model, activating only 3B parameters per token, significantly outperforms peers like Qwen and Gemma on agentic coding tasks. A quantized 9B-Mobile build is also available for on-device deployment on iPhone and Android.
Related event: Ornith-1.5 Release: 397B MoE Self-Improvement Targets Claude Opus(24 posts)→
More from Models
- Prediction: frontier AI revenue growth could slow even as AI usage keeps rising — yi111 · 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