Project page · Code · Webdev-Bench · Paper
WebCoder-27B is a general frontend development agent, trained from Qwen3.8-27B with artifact-grounded agentic reinforcement learning. It is the model released with the paper
WebCoder: Scaling General Frontend Development with Artifact-Grounded Agentic Reinforcement Learning Zijun Dou*, Zhen Yang*, Xijun Liu, Dongzhuoran Zhou, Aohan Zeng, Jie Tang *Core contributors.
Real-world frontend development requires an agent to compose reproduction, generation, modification and repair over an evolving application state. WebCoder assesses all of these activities through their effects on a shared executable artifact and on its satisfaction of the task requirements.
| Model | Vision2Web Avg | Webdev-Bench RS | Webdev-Bench Avg | Webdev-Bench DSR |
|---|---|---|---|---|
| Claude-Opus-4.8 | 62.5 | 65.1 | 73.7 | 100.0% |
| GPT-5.4 | 57.9 | 59.6 | 70.8 | 100.0% |
| Qwen3.8-27B (base) | 41.1 | 64.8 | 72.8 | 95.0% |
| WebCoder-27B | 62.4 | 72.8 | 79.8 | 100.0% |
RS is requirement satisfaction and DSR the delivery success rate. The full table, with every baseline and every sub-metric, is in the paper and on the project page.
WebCoder-27B keeps the architecture (Qwen3_5ForConditionalGeneration), tokenizer, chat
template and processor configuration of its base model, so it is served the same way as
Qwen3.8-27B — for example with vLLM or SGLang. See the
Qwen3.8-27B model card for serving commands and
API examples.
vllm serve Roy-DOU/WebCoder-27B --tensor-parallel-size 4
generation_config.json sets temperature=1.0, top_p=0.95, top_k=20.
The model was trained as an agent: it acts through tools in a development environment over many turns, and is at its best in that setting rather than in single-turn chat.
Released under the Apache License 2.0, the license of the base model. See LICENSE.
@article{dou2026webcoder,
title = {WebCoder: Scaling General Frontend Development with Artifact-Grounded Agentic Reinforcement Learning},
author = {Dou, Zijun and Yang, Zhen and Liu, Xijun and Zhou, Dongzhuoran and Zeng, Aohan and Tang, Jie},
journal = {arXiv preprint arXiv:2610.23104},
year = {2026}
}
model-00004-of-00011.safetensors 5.4 GBmodel-00000-of-00011.safetensors 5.4 GBmodel-00002-of-00011.safetensors 5.3 GBmodel-00003-of-00011.safetensors 5.3 GBmodel-00005-of-00011.safetensors 5.3 GBmodel-00001-of-00011.safetensors 5.3 GBmodel-00007-of-00011.safetensors 5.3 GBmodel-00009-of-00011.safetensors 5.3 GBmodel-00006-of-00011.safetensors 5.3 GBmodel-00008-of-00011.safetensors 5.2 GBmodel-00010-of-00011.safetensors 2.5 GBQwen/Qwen3.8-27B