# Ant Group Releases GUI-Trained LBS-27B Vision Model

Published 2026-10-27 · AI.info Team · AI.info

> Ant Group’s inclusionAI released LBS-27B, a vision-language model adapted using synthetic GUI-grounding data, on October 26. The team reports results on five visual benchmarks and publishes the weights under Apache 2.0, while noting that live app control requires a separate executor.

## 89.13% on HR-Bench 4K

Ant Group’s inclusionAI says its LBS-27B model scored 89.13% on HR-Bench 4K, a benchmark for answering questions about high-resolution images. The model, released on October 26, also scored 87.75% on HR-Bench 8K and 81.15% on ScreenSpot-Pro, which measures accuracy in locating interface elements. Its weights and project software are published under the Apache 2.0 license.

Source [huggingface.co](https://huggingface.co/inclusionAI/LBS-27B)

LBS-27B is based on Qwen3.8-27b and is designed to inspect images by selecting regions, zooming in and revisiting earlier crops. inclusionAI describes the approach as transferring a visual-observation policy learned through graphical user interface (GUI) grounding to general visual question answering. The training claim applies to the data used for this adaptation; the model card does not say the underlying Qwen base model was trained only on GUI data.

> “It learns to select and inspect image regions through GUI grounding, then transfers this observation policy to general-domain visual question answering and high-resolution perception.”
>
> [inclusionAI, LBS-27B model card](https://huggingface.co/inclusionAI/LBS-27B)

## Training stays within synthetic GUI data

The team says it used approximately 10,000 supervised fine-tuning examples for a cold start, then trained with 80 steps of Group Relative Policy Optimization, or GRPO. Each step used a batch size of 64 and eight rollouts per prompt. The model card says those training stages used synthetic GUI-grounding data, without general-domain data or visual question-answering examples.

During use, LBS can request as many as two separate crops in a turn, with a limit of three crop calls per episode. It can refine a crop or return to the original image, an approach intended to help it locate small interface targets and examine detail in high-resolution images. The released checkpoint is available for serving with a compatible vLLM setup; inclusionAI’s example uses four devices.

## The scores come with comparison limits

The results cover five evaluations: ScreenSpot-Pro, OS-World-G (Refine), PerceptionBench, and HR-Bench at 4K and 8K. On OS-World-G, the reported 84.57% action accuracy includes refusal cases. PerceptionBench’s 59.67% judge accuracy comes from 3,000 records scored by a self-hosted Deepseekv4-flash-0731 judge.

Those figures are not a controlled head-to-head comparison with other models, the release notes say. The reference results use different inference setups, and the PerceptionBench comparisons use a different judge, GPT-oss-120B; repeated judgments may also vary. The score table therefore records inclusionAI’s reported results, not proof that LBS-27B outperforms a named competitor under identical conditions.

## Coordinates do not operate an app by themselves

LBS returns plain-text crop requests and normalized coordinates for interface targets. A client must carry out the crop requests, return the images and coordinate mappings, and—if the goal is to operate a live application—send the resulting action to a separate executor. The model locates a target; it does not itself click through an app.

The weights are downloadable, but third-party datasets and screenshots remain subject to their original licenses and terms. The concrete test ahead is whether the GUI-trained observation policy transfers reliably to visual questions outside interfaces when independent teams evaluate it with matched benchmarks and scoring protocols.

## Sources

1. Original source [Hugging Face · page 1](https://huggingface.co/inclusionAI/LBS-27B) huggingface.co

Other pages read

2. [Hugging Face · page 2](https://huggingface.co/inclusionAI/LBS-27B/commits/main) huggingface.co
3. [GitHub](https://github.com/inclusionAI/UI-Venus/blob/LBS/docs/BENCHMARK_OVERVIEW.md) github.com

## Related stories

- [NVIDIA’s 120B Nemotron 3.5 Super VL is available on SageMaker](https://ai.info/news/nvidia-nemotron-35-super-vl-sagemaker-jumpstart)
- [Audit Finds Benchmark Graders Shift Scores by 22 Points](https://ai.info/news/audit-benchmark-graders-shift-multimodal-scores-22-points)
- [Liquid AI Releases Six Models on One Small-Model Backbone](https://ai.info/news/liquid-ai-lfm3-shared-backbone-six-models)
- [Bria Releases Fibo 2.0, an 8B Model for Image Editing and Generation](https://ai.info/news/bria-fibo-2-open-8b-image-model)
- [OpenAI Releases GPT-6.1 Terra at Half the API Price](https://ai.info/news/openai-gpt-6-1-terra-cheaper-computer-use)

## Explore

[More articles](https://ai.info/news)

---

Canonical: https://ai.info/news/ant-group-releases-gui-trained-lbs-27b-vision-model
