Ornith-1.0-397B
MoE workstation~397B total params, MoE - the original Ornith-1.0 flagship, released 2026-06-25 and superseded by Ornith-1.5-397B. Self-scaffolding: the model jointly learns to generate solution rollouts and the task-specific harnesses that guide them. 262K context, MIT-licensed on HuggingFace at ornith-ai/Ornith-1.0-397B (FP8 and GGUF quantizations).
- Coding (vendor self-reported): Terminal-Bench 2.1 77.5, SWE-bench Verified 82.4, NL2Repo 48.2.
- Reasoning: HLE 30.2, GPQA-Diamond 88.1.
- Agentic: MCP-Atlas 76.4, Toolathlon-Verified 43.2, ClawEval 77.1.
Superseded by Ornith-1.5-397B (TB-2.1 86.1, SWE-bench Verified 86.0). Prefer 1.5 for new work. Server-class only.
- 397.0B
- 262k
- mit
- 🇺🇸 USA
- Jun 2026
Benchmark scores
Vendor-reported - from the developer's own model card / tech report
Vendor-reported - from the developer's own model card / tech report
Ran this model on your own hardware? Join free and add your measured tok/s to the community numbers.
Related models
Save your hardware and every model page answers the real question: will it run on your machine, and how fast?
Join free - save your rig →Or run it in the cloud
No per-token API provider pricing tracked for Ornith-1.0-397B yet. For flagship list prices, see the calculator.
Inference cost over time
Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.