Ornith-1.0-397B

Ornith AI released Ornith-1.0-397B, a 397-billion-parameter mixture-of-experts model with 262K context, on 2026-06-25, now superseded by Ornith-1.5-397B. The model self-reports coding scores of 77.5 on Terminal-Bench 2.1, 82.4 on SWE-bench Verified, and 48.2 on NL2Repo, reasoning scores of 30.2 on HLE and 88.1 on GPQA-Diamond, and agentic scores of 76.4 on MCP-Atlas, 43.2 on Toolathlon-Verified, and 77.1 on ClawEval. It is MIT-licensed on HuggingFace at ornith-ai/Ornith-1.0-397B, with FP8 and GGUF quantizations available.

Ornith-1.0-397B MoE workstation ~397B total params, MoE - the original Ornith-1.0 flagship, released 2026-06-25 and superseded by Ornith-1.5-397B.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 Superseded by Ornith-1.5-397B TB-2.1 86.1, SWE-bench Verified 86.0 .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. coding reasoning agentic - 397.0B - 262k - mit - 🇺🇸 USA - Jun 2026 Scores Coding 88 Reasoning 86 Tool calling 82 General 85 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 /calculator . PRICE HISTORY 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. Loading price history...