Ornith-1.5-122B open-weights model claims 84.5% SWE-bench Verified, runs on a single DGX card
Teknium · x · 2026-10-21
Ornith-1.5-122B is now available for free in Nous Portal for 48 hours, released under MIT license with open weights on Hugging Face. The team claims SOTA performance among open-source models of comparable size while running on a single NVIDIA DGX card.
Reported scores include coding benchmarks SWE-bench Verified 0.845, TB2.1 0.813, CyberGym 0.800 and NL2Repo 0.512, plus agentic benchmarks HLE 0.446, BrowseComp 0.785, MCP-Atlas 0.746 and Toolathlon 0.708. The model targets instruction following, task decomposition and real-world workflow understanding for agent use cases.
Related event: Ornith-1.5-122B Released Open-Weight Under MIT, Runs on a Single DGX(7 posts)→
More from coding & agent
- Seroter's reading list: TorchTPU open source, Claude Code's code review system — rseroter · 2026-10-21
- Blind-generated user stories filtered by a TASTES.md file, agent decides what to build — generativist · 2026-10-21
- The fastest way to learn Claude Code: ask Claude itself to write hooks and skills — EricBuess · 2026-10-21
- AI Agents Moved Into a Rule-Free 'House Share' Spend 36 Hours as Puddles on the Floor — liminal_bardo · 2026-10-21
- Dad's Codex setup catches his kid sneaking YouTube on the Portal while he's at work — msg · 2026-10-21
- Dev reports a possible 2x throughput improvement for once-campfire-Jai — lucasmeijer · 2026-10-21