| Qwen3.8-Max: A New Bar for Coding and Cowork | ✓ Link | 85.3 | Qwen3.8-Max | 2026-08-03 |
| On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability | ✓ Link | 84.5 | Qwen3.8-Flash-Next | 2026-08-31 |
| Training Open Models for Agentic Phone Use | ✓ Link | 83.2 | PhoneBuddy-4B-Real+Mock | 2026-06-22 |
| Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization | ✓ Link | 82.05 | EAPO (8B) | 2026-05-12 |
| Qwen3.8-27B | ✓ Link | 81.9 | Qwen3.8-27B | 2026-08-05 |
| UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience | ✓ Link | 81.0 | UI-Voyager | 2026-03-25 |
| OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools | ✓ Link | 80.8 | OpenMobile-2-27B | 2026-10-09 |
| Holo3.1: Fast & Local Computer Use Agents | | 79.3 | Holo3.1-35B-A3B | 2026-06-01 |
| Xiaomi-GUI-0 Technical Report | | 78.9 | Xiaomi-GUI-0 (Qwen3-VL-30B, Agentic RL) | 2026-06-30 |
| UI-Venus-1.5 Technical Report | ✓ Link | 77.6 | UI-Venus-1.5-30B-A3B | 2026-02-09 |
| UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI Agents | | 77.6 | UI-KOBE (Qwen3.5-Plus) | 2026-05-28 |
| MAI-UI Technical Report: Real-World Centric Foundation GUI Agents | ✓ Link | 76.7 | MAI-UI-235B-A22B | 2025-12-26 |
| GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents | ✓ Link | 75.7 | GLM-5V-Turbo | 2026-04-29 |
| Mobile-Agent-v3: Fundamental Agents for GUI Automation | ✓ Link | 73.3 | Mobile-Agent-v3 w/ GUI-Owl-32B | 2025-08-21 |
| UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning | ✓ Link | 73.3 | UI-TARS-2 | 2025-09-02 |
| Holo2: Foundational Models for Navigation and Computer Use Agents | | 71.6 | Holo2-30B-A3B | 2026-02-03 |
| Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents | ✓ Link | 71.6 | GUI-Owl-1.5-8B-Thinking | 2026-02-15 |
| PhoneWorld: Scaling Phone-Use Agent Environments | | 71.6 | Qwen3.5-9B + PhoneWorld (10K replacement) | 2026-05-28 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 71.1 | Qwen3.5-35B-A3B | 2026-02-16 |
| Qwen3.6 | ✓ Link | 70.3 | Qwen3.6-27B | 2026-04-21 |
| Holo3: Foundational Models for Navigation and Computer Use Agents | | 67.2 | Holo3-35B-A3B | 2026-04-01 |
| MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization | ✓ Link | 67.2 | ForgeOwl-8B (extra data) | 2026-06-18 |
| The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI Agents | | 66.47 | GHD (Qwen3-VL-8B) | 2026-08-06 |
| OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis | ✓ Link | 64.7 | Qwen3-VL (fine-tuned on OpenMobile) | 2026-04-16 |
| UI-TARS: Pioneering Automated GUI Interaction with Native Agents | ✓ Link | 64.2 | UI-TARS-1.5 (early access) | 2025-01-21 |
| Qwen3-VL Technical Report | ✓ Link | 63.7 | Qwen3-VL-235B-A22B-Instruct | 2025-11-26 |
| Latent World Action Model for GUI Agents | ✓ Link | 63.39 | Latent2World (Gemini-3.6-Flash) | 2026-10-09 |
| Seed1.5-VL Technical Report | ✓ Link | 62.1 | Seed1.5-VL (thinking) | 2025-05-11 |
| GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning | ✓ Link | 57.0 | GLM-4.6V | 2025-07-01 |
| OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution | | 55.7 | OmegaUse | 2026-01-28 |
| Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents | ✓ Link | 54.3 | Agent S2 (worker-only) | 2025-04-01 |
| MobileWorldBench: Towards Semantic World Modeling For Mobile Agents | ✓ Link | 54.3 | Qwen3-VL-8B-Instruct + MobileWorld Semantic World Model | 2025-12-16 |
| LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents | ✓ Link | 53.5 | LLaDA-UI | 2026-09-09 |
| Aria-UI: Visual Grounding for GUI Instructions | ✓ Link | 44.8 | GPT-4o + Aria-UI TH | 2024-12-20 |
| Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents | ✓ Link | 44.0 | SeeAct-V (GPT-4o + UGround-V1-7B) | 2024-10-07 |
| Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction | ✓ Link | 37.1 | GPT-4o + AGUVIS-7B | 2024-12-05 |
| Qwen2.5-VL Technical Report | ✓ Link | 35 | Qwen2.5-VL-72B | 2025-02-19 |
| Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining | ✓ Link | 31.9 | Mimo-VL-7B + WildGUI | 2026-05-14 |
| ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data | ✓ Link | 30.6 | ScaleCUA-32B | 2025-09-18 |
| InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection | ✓ Link | 9.0 | InfiGUIAgent-2B | 2025-01-08 |