Ornith-1.5-122B released open-source under MIT, hits 84.5% on SWE-bench on a single DGX card
aftahi_ai · x · 2026-10-21
Ornith-1.5-122B has been released as an open-weights model under the MIT license, claiming frontier-level capability while running inference efficiently on a single NVIDIA DGX card.
Reported benchmarks:
- Coding: SWE-bench Verified 0.845, TB2.1 0.813, CyberGym 0.800, NL2Repo 0.512
- Agentic: HLE 0.446, BrowseComp 0.785, MCP-Atlas 0.746, Toolathlon 0.708
The team highlights stronger instruction following, task decomposition, and real-world workflow understanding, claiming SOTA among open-source models of comparable size. Weights are available on Hugging Face.
More from coding & agent
- PHP hit by two unauthenticated RCE flaws; ProjectDiscovery launches free internet-wide alert service — cyb3rops · 2026-10-23
- Modal open-sources Spindle, a Tinker-compatible training server that charges GPU time instead of tokens — josh_wills · 2026-10-23
- Testing the Azure Cosmos DB Agent Kit: what it found reviewing a Claude-built app, in RUs saved — adnan_hashmi · 2026-10-23
- Dev ditches endless chat threads for a visual dashboard to manage her AI agents — Salmaaboukarr · 2026-10-23
- Warp cuts coding agent verification bottleneck with per-agent computer-use and clip reviews — vikvang1 · 2026-10-23
- Computer Use Is Solved; Specifying Goals Is the New Bottleneck for Agents — alishbaimran_ · 2026-10-23