metadata
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
base_model:
- Qwen/Qwen3-8B
datasets:
- DedeProGames/Terminal-Reasoning-SFT
tags:
- text-generation
- transformers
- agent
- reasoning
- terminal
- swe-bench
OpenAgent
OpenAgent is an open-source effort to curate the best datasets for training agents.
OpenAgent is a model trained for agentic tasks such as Terminal-Bench 2.0 and SWE-Bench.
It was trained on the dataset:
OpenAgent 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 |
| OpenAgent | 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 |
Hugging Face
- Model:
DedeProGames/OpenAgent - Dataset:
DedeProGames/Terminal-Reasoning-SFT
OpenAgent is an open-source effort focused on building stronger agentic models through better datasets, practical training, and real benchmark evaluation.