Open-source Ornith-1.5 achieves Claude Opus-level performance via self-improvement

aftahi_ai · x · 2026-08-19

Ornith-1.5, a family of open-source LLMs (9B Dense, 35B/397B MoE), introduces a complete end-to-end self-improvement loop. It achieves SOTA among comparable open-source models and rivals Claude Opus 4.8 in reasoning, agentic, and coding tasks.

Key benchmarks include:

The model extends the self-scaffolding strategies from Ornith-1.0.

Related event: Open-Source Ornith-1.5 Family Released, 397B MoE Claims Claude Opus-Level Performance(13 posts)→

Original post →

More from Models

Models channel →