# Ornith-1.5: an open model trained on tasks it set itself

URL: https://ai-pulse.aglaganova.com/blog/ornith-1-5-an-open-model-trained-on-tasks-it-set-itself
Published: 2026-10-22
Author: Roman Aglaganov, Full-stack developer
Category: Models
Region: Global
Tags: open-weights, coding

> The newest member of the Ornith-1.5 family is a 122-billion-parameter model under the permissive MIT licence, built to run on a single GPU. Its makers say it was trained largely on problems it invented and solved.

![Illustration: a black loop arrow circling a cluster of grey squares, with a small red square at the point where the loop closes](https://ai-pulse.aglaganova.com/api/media/file/ornith-1.png)

A team publishing as Ornith AI has released Ornith-1.5-122B on Hugging Face, with compressed versions for smaller hardware posted on 20 October. It is the newest member of a family that also includes 9-billion, 35-billion and 397-billion-parameter models, released in August.

## What it is

The model is a mixture of experts, which uses only part of its 122 billion parameters for each word, and its makers say it is designed to run on a single GPU. It is released under the MIT licence, which lets anyone use, change and sell products built on it. It is a reasoning model: it thinks through a problem before answering.

## The training idea

Ornith-1.0 was built on top of open models from Alibaba (Qwen3.5) and Google (Gemma 4). For 1.5, the team says it extended a “self-improvement loop”: rather than relying on a fixed set of tasks written by people, the model generates new training tasks, builds the tools to tackle them, tries solutions and learns from the results through reinforcement learning.

## The claims

On its model card, the team reports 84.5% on SWE-bench Verified and 76.9% on SWE-bench Pro, tests of fixing real software bugs, with safeguards meant to stop the model gaming the tests. It does not lead everywhere: on TerminalBench 2.1 it scores 81.2, below Qwen3.8-Flash-Next and DeepSeek-V4-Flash in the same table. These are the developers’ own results.

## Why it matters

Open models that companies can run on their own hardware keep getting more capable, and a model that can invent its own practice problems needs less expensive human-written data. If that approach holds up under outside testing, it lowers one of the biggest costs of building a strong model.

## Sources

- [Hugging Face: ornith-ai/Ornith-1.5-122B](https://huggingface.co/ornith-ai/Ornith-1.5-122B)
- [Ornith AI: Ornith-1.5, from self-scaffolding to self-improvement](https://ornith.ai/ornith_1_5.html)