Ornith-1.5-122B open weights debut: 84.5% SWE-bench Verified on a single DGX card
aftahi_ai · x · 2026-10-21
Ornith-1.5-122B, released under MIT license, claims SOTA among similarly sized open models while running on a single NVIDIA DGX card. Self-reported scores: SWE-bench Verified 84.5%, TB2.1 81.3%, CyberGym 80.0%, NL2Repo 51.2%; agentic: HLE 44.6%, BrowseComp 78.5%, MCP-Atlas 74.6%, Toolathlon 70.8%.
The pitch is no tradeoff between strong and fast: better instruction following, task decomposition, and real-world workflow understanding with efficient inference. Weights are on Hugging Face; notable debut from a new open-weights player (numbers are self-reported).
More from Models
- GPT-6 Astra and Claude Fable 5.1 write $10,000 research papers — experts reject all — sayashk · 2026-10-21
- GitHub Copilot's HydraFusion Orchestrates Multiple Models Per Task — WirelessLife · 2026-10-21
- OpenVLHarness turns any MLLM into a visual reasoner, +9.9 points across 22 datasets — yining_hong · 2026-10-21
- User claims Gemini analyzed his tennis match video and improved his game — zacharynado · 2026-10-21
- Opus 5.5 tops OpenRouter spending in 20 of 29 task categories — mmurph · 2026-10-21
- Meta team builds open-source 30B LLM from scratch in months, hails 'second era' — TimDarcet · 2026-10-21