| Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents | | 97.5 | Qwen-UI-Agent (27B) | 2026-07-30 |
| MAI-UI Technical Report: Real-World Centric Foundation GUI Agents | ✓ Link | 96.5 | MAI-UI-32B | 2025-12-26 |
| OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution | | 96.3 | OmegaUse-G | 2026-01-28 |
| UI-Venus-1.5 Technical Report | ✓ Link | 96.2 | UI-Venus-1.5-30B-A3B | 2026-02-09 |
| GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives | ✓ Link | 96.15 | GroundingPI | 2026-09-30 |
| Holo2: Foundational Models for Navigation and Computer Use Agents | | 95.9 | Holo2-235B-A22B | 2026-02-03 |
| POINTS-GUI-G: GUI-Grounding Journey | ✓ Link | 95.7 | POINTS-GUI-G-8B | 2026-02-06 |
| Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding | | 95.68 | Quality-Aware Self-Distillation | 2026-06-16 |
| GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed | ✓ Link | 95.6 | GroundAnything | 2026-09-30 |
| Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents | ✓ Link | 95.3 | GUI-Owl-1.5-32B-Instruct | 2026-02-15 |
| Seed1.5-VL Technical Report | ✓ Link | 95.2 | Seed1.5-VL (thinking) | 2025-05-11 |
| GTA1: GUI Test-time Scaling Agent | ✓ Link | 95.2 | GTA1-32B | 2025-07-08 |
| GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning | ✓ Link | 95.2 | GroundGUI-8B | 2026-10-13 |
| Step-GUI Technical Report | ✓ Link | 95.1 | Step-GUI-8B | 2025-12-17 |
| GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL | ✓ Link | 94.8 | GUI-Libra-8B + Mix Grounding 20K (extra data) | 2026-02-25 |
| ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data | ✓ Link | 94.7 | ScaleCUA-32B | 2025-09-18 |
| Fara-1.5: Scalable Learning Environments for Computer Use Agents | ✓ Link | 94.4 | Fara1.5-27B | 2026-06-18 |
| UI-TARS: Pioneering Automated GUI Interaction with Native Agents | ✓ Link | 94.2 | UI-TARS-1.5 (early access) | 2025-01-21 |
| MolmoPoint: Better Pointing for VLMs with Grounding Tokens | ✓ Link | 93.9 | MolmoPoint-GUI-8B (64crops) | 2026-03-30 |
| Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale | | 93.6 | Intern-S1-Pro | 2026-03-26 |
| InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization | ✓ Link | 93.5 | InfiGUI-G1-7B (extra data) | 2025-08-07 |
| EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience | ✓ Link | 93.47 | EvoCUA-OpenCUA-72B | 2026-01-22 |
| OpenCUA: Open Foundations for Computer-Use Agents | ✓ Link | 93.4 | OpenCUA-32B | 2025-08-12 |
| Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence | ✓ Link | 93.4 | Nemotron 3 Nano Omni | 2026-04-27 |
| GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding | ✓ Link | 93.3 | GUI-G²-7B | 2025-07-21 |
| Mobile-Agent-v3: Fundamental Agents for GUI Automation | ✓ Link | 93.2 | GUI-Owl-32B | 2025-08-21 |
| FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection | ✓ Link | 93.1 | FocusUI-7B (r=100%) | 2026-01-07 |
| Kimi-VL Technical Report | ✓ Link | 92.8 | Kimi-VL-A3B-Instruct | 2025-04-10 |
| STEP3-VL-10B Technical Report | ✓ Link | 92.61 | Step3-VL-10B | 2026-01-14 |
| UItron: Foundational GUI Agent with Advanced Perception and Planning | ✓ Link | 92.0 | UItron-72B | 2025-08-29 |
| MolmoWeb: Open Visual Web Agent and Open Data for the Open Web | ✓ Link | 91.8 | MolmoWeb-Ground (8B) | 2026-04-09 |
| Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis | ✓ Link | 91.7 | Jedi-7B | 2025-05-19 |
| GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models | ✓ Link | 91.0 | UI-TARS 1.5* + ICM-r2 | 2026-01-26 |
| UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning | ✓ Link | 90.88 | UI-MOPD | 2026-07-05 |
| LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents | ✓ Link | 90.7 | LLaDA-UI | 2026-09-09 |
| PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding | ✓ Link | 90.6 | Qwen3-VL (2B) with PixelPrune (+KD) | 2026-04-01 |
| MiMo-VL Technical Report | ✓ Link | 90.5 | MiMo-VL-7B-RL | 2025-06-04 |
| Grounding Computer Use Agents on Human Demonstrations | ✓ Link | 90.4 | GroundNext-7B (RL) | 2025-11-10 |
| DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents | ✓ Link | 90.33 | DeskForge-Qwen3.5-4B | 2026-10-01 |
| Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning | ✓ Link | 90.3 | SE-GUI-7B (extra data) | 2025-05-18 |
| UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization | ✓ Link | 90.0 | UI-Copilot-7B | 2026-04-15 |
| UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning | ✓ Link | 89.5 | UI-R1-E-3B | 2025-03-27 |
| Fara-7B: An Efficient Agentic Model for Computer Use | ✓ Link | 89.3 | Fara-7B | 2025-11-24 |
| BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent | ✓ Link | 89.1 | BTL-UI 7B | 2025-09-19 |
| Detect Anything via Next Point Prediction | ✓ Link | 88.4 | Rex-Omni | 2025-10-14 |
| LongCat-Next: Lexicalizing Modalities as Discrete Tokens | ✓ Link | 88.3 | LongCat-Next (A3B, 68.5B) | 2026-03-29 |
| Phi-4-reasoning-vision-15B Technical Report | ✓ Link | 88.2 | Phi-4-reasoning-vision-15B | 2026-03-04 |
| AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines | ✓ Link | 86.16 | AutoWebWorld 7B | 2026-02-15 |
| Vision as Unified Multimodal Generation | ✓ Link | 85.9 | SenseNova-Vision | 2026-07-07 |
| OS-ATLAS: A Foundation Action Model for Generalist GUI Agents | ✓ Link | 84.12 | OS-Atlas-Base-7B | 2024-10-30 |
| Continual GUI Agents | ✓ Link | 81.2 | GUI-AiF (Qwen2.5VL-3B) | 2026-01-28 |
| GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction | ✓ Link | 81.1 | GoClick-L (0.8B) | 2026-04-27 |