JanusCoder-8B
💻Github Repo • 🤗Model Collections • 📜Technical Report
Introduction
We introduce JanusCoder and JanusCoderV, a suite of open-source foundational models designed to establish a unified visual-programmatic interface for code intelligence. This model suite is built upon open-source language models (such as Qwen3-8B and 14B) and multimodal models (such as Qwen2.5-VL and InternVL3.5-8B). The JanusCoder series is trained on JANUSCODE-800K—the largest multimodal code corpus to date, generated by an innovative synthesis toolkit, covering everything from standard charts to complex interactive Web UIs and code-driven animations. This enables the models to uniformly handle diverse visual-programmatic tasks, such as generating code from textual instructions, visual inputs, or a combination of both, rather than building specialized models for isolated tasks. JanusCoder excels at flexible content generation (like data visualizations and interactive front-ends) as well as precise, program-driven editing of visual effects and complex animation construction.
Model Downloads
| Model Name | Description | Download |
|---|---|---|
| 👉 JanusCoder-8B | 8B text model based on Qwen3-8B. | 🤗 Model |
| JanusCoder-14B | 14B text model based on Qwen3-14B. | 🤗 Model |
| JanusCoderV-7B | 7B multimodal model based on Qwen2.5-VL-7B. | 🤗 Model |
| JanusCoderV-8B | 8B multimodal model based on InternVL3.5-8B. | 🤗 Model |
Performance
We evaluate the JanusCoder model on various benchmarks that span code interlligence tasks on multiple PLs:
| Model | JanusCoder-8B | Qwen3-8B | Qwen2.5-Coder-7B-Instruct | LLaMA3-8B-Instruct | GPT-4o |
|---|---|---|---|---|---|
| PandasPlotBench (Task) | 80 | 74 | 76 | 69 | 85 |
| ArtifactsBench | 39.6 | 36.5 | 26.0 | 36.5 | 37.9 |
| DTVBench (Manim) | 9.70 | 6.20 | 8.56 | 4.92 | 10.60 |
| DTVBench (Wolfram) | 6.07 | 5.18 | 4.04 | 3.15 | 5.97 |
Quick Start
Transformers
The following provides demo code illustrating how to generate text using JanusCoder-8B.
Please use transformers >= 4.55.0 to ensure the model works normally.
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_name = "internlm/JanusCoder-8B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto")
messages = [
{
"role": "user",
"content": [
{"type": "text", "text": "Create a line plot that illustrates function y=x."},
],
}
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)
generate_ids = model.generate(**inputs, max_new_tokens=32768)
decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)
print(decoded_output)
Citation
🫶 If you are interested in our work or find the repository / checkpoints / benchmark / data helpful, please consider using the following citation format when referencing our papers:
@article{sun2025januscoder,
title={JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence},
author={Sun, Qiushi and Gong, Jingyang and Liu, Yang and Chen, Qiaosheng and Li, Lei and Chen, Kai and Guo, Qipeng and Kao, Ben and Yuan, Fei},
journal={arXiv preprint arXiv:2510.23538},
year={2025}
}
@article{sun2024survey,
title={A survey of neural code intelligence: Paradigms, advances and beyond},
author={Sun, Qiushi and Chen, Zhirui and Xu, Fangzhi and Cheng, Kanzhi and Ma, Chang and Yin, Zhangyue and Wang, Jianing and Han, Chengcheng and Zhu, Renyu and Yuan, Shuai and others},
journal={arXiv preprint arXiv:2403.14734},
year={2024}
}
@article{chen2025interactscience,
title={InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation},
author={Chen, Qiaosheng and Liu, Yang and Li, Lei and Chen, Kai and Guo, Qipeng and Cheng, Gong and Yuan, Fei},
journal={arXiv preprint arXiv:2510.09724},
year={2025}
}
@article{sun2025codeevo,
title={CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback},
author={Sun, Qiushi and Gong, Jinyang and Li, Lei and Guo, Qipeng and Yuan, Fei},
journal={arXiv preprint arXiv:2507.22080},
year={2025}
}