OrionLLM/Terminus-Qwen3-8b

Terminus

OpenAgent is an open-source effort to curate the best datasets for training agents.

---

Terminus is a model trained for terminal agentic tasks such as Terminal-Bench 2.0 and SWE-Bench.

It was trained on the dataset:

• OrionLLM/OpenAgentInstruct

Terminus is designed to improve performance on terminal-based reasoning, software engineering, and tool-using workflows.

---

Benchmarks

Model	Harness	Terminal-Bench 2.0	SWE-Bench Verified
Qwen3-8B	Terminus-2	0.0	0.7
Terminus-Qwen3-8b	Terminus-2	4.9	15.7
Qwen3-32B	Terminus-2	1.9	5.7
Qwen/Qwen3-Coder-30B-A3B-Instruct	OpenHands	10.1	49.2

---

OpenAgent is an open-source effort focused on building stronger agentic models through better datasets, practical training, and real benchmark evaluation.