Ornith-1.5-35B Outperforms Qwen and Gemma in Reasoning and Coding

alejandroll10 · x · 2026-08-20

Ornith-1.5-35B model released, significantly outperforming its similar-sized peer Qwen 3.6-35B across reasoning, coding, and agentic benchmarks. Despite activating only 3B parameters per token, it also outperforms dense models like Gemma 4-31B and Meta's Muse Glimmer-30B by wide margins.

Related event: DeepReinforce Open-Sources Ornith-1.5 Family, Flagship 397B Claims Claude Opus 4.8 Parity(15 posts)→

Original post →

More from Models

Models channel →