--- library_name: transformers license: apache-2.0 pipeline_tag: text-generation base_model: - Qwen/Qwen3.5-9B --- ![Banner](https://cdn-uploads.huggingface.co/production/uploads/685ea8ff7b4139b6845ce395/vn7pEOMUQ9-5vYgJQ4oVh.png) ## Introduction We are proud to introduce **OxCoder-9B**, our lightweight coding model for long-horizon tasks, agentic coding, and agentic reasoning. Despite featuring only 9 billion parameters, OxCoder-9B marks a substantial leap in agentic capabilities — particularly in **Agentic Terminal** and **Agentic Coding** tasks — punching far above its weight class and rivaling models many times its size. This release represents our strongest commitment yet to delivering frontier-level agentic performance in a compact, efficient, and openly accessible package. - **Trained on Frontier Agent Traces:** Built from Fable-5.1 and GLM-5.3 agentic coding trajectories across Claude Code, OpenCode and Codex — OxCoder-9B has been distilled from some of the most capable agentic systems available, giving it a unique advantage in real-world software engineering scenarios. - **262K Native Context:** Equipped with a full 262,144 token native context window, enabling the model to handle complex, multi-file codebases and long-horizon reasoning tasks with ease. - **Error Recovery:** Learns read-before-write patterns, responds to LSP diagnostics, and applies minimal edit diffs instead of full rewrites — making it robust in iterative coding environments where precision matters. - **Front-end Reasoning:** OxCoder-9B exhibits remarkably strong front-end reasoning capabilities for its size, demonstrating a deep understanding of UI logic, component architecture, and web-native patterns that is rare in sub-10B models. ![Coding Performance Evaluation](./assets/coding-performance-evaluation.png) ## Benchmark
OxCoder-9B Ornith-1.5-9B Ornith-1.0-9B Qwen3.5-9B Gemma-4-31B
Coding
Agentic terminal coding
Terminal-Bench 2.1 (Terminus-2)
 49.6 46.2 43.1 21.3 42.1
Agentic terminal coding
Terminal-Bench 2.1 (Claude Code)
 50.8 47.0 40.6 18.9 —
Agentic coding
SWE-bench Verified
 73.5 70.6 69.4 53.2 52.0
Real-world software engineering
SWE-bench Pro
 49.1 47.5 42.9 31.3 35.7
Repo-level code generation
NL2Repo
 36.2 32.4 27.2 16.2 15.5
Reasoning
Expert-level reasoning
HLE (no tools)
 21.2 20.2 16.8 14.7 19.5
Tool-augmented reasoning
HLE (with tools)
 32.8 30.5 26.4 24.5 26.5
Scientific reasoning
GPQA Diamond
 86.9 86.4 82.5 81.7 84.3
Agentic
Multi-tool orchestration
MCP-Atlas
 56.7 54.2 49.4 46.8 55.0
Web browsing and research
BrowseComp
 57.4 56.4 44.8 41.5 —
Real-user agentic coding
ClawEval
 67.8 66.5 63.1 53.2 48.5

* All results reported for OxCoder-9B are averaged over five independent runs. A dash (—) means the score was not reported for that model.
* Terminal-Bench 2.1 (Terminus-2): We evaluate Terminal-Bench 2.1 using the Harbor/Terminus-2 framework with parser=json, temperature=1.0, top_p=1.0, and a 256K context window. Each run uses a 2-hour timeout with 32 CPU cores and 32GB RAM.
* Terminal-Bench 2.1 (Claude Code): We evaluate Terminal-Bench 2.1 using Claude Code 2.1.126 with parser=json, temperature=1.0, top_p=1.0.
* SWE-bench Verified and Pro: using the OpenHands harness with temp=1.0, top_p=0.95, 256K context window. Anti-hacking safeguards are applied throughout evaluation: Git history is removed from the local repository image to prevent access to prior solutions or commits; network access is disabled, preventing the model from retrieving external information or resources.
* NL2Repo: with temperature=1.0, top_p=1.0, 256K context, 48K output. Access to the specified GitHub repositories and pip packages is blocked to prevent reward hacking.
* HLE: Evaluated using GLM-5.3 as the judge model.
* MCP-Atlas: Evaluated using GLM-5.3 as the judge model.
* ClawEval: temp=0.6 and 256K context.
* Baseline scores for Ornith-1.5-9B, Ornith-1.0-9B, Qwen3.5-9B and Gemma-4-31B are taken from the Ornith-1.5-9B model card and were produced under that team's evaluation settings, which differ from ours on some benchmarks (context window, timeouts and judge model).

---
**OxCoder-9B** is developed by **[OrionLLM](https://huggingface.co/OrionLLM)** and released under the Apache 2.0 License.