GUI Agent Interaction on OSWorld (Step Success Rate)
42.9Success Rate (Max Steps: 15)Claude 4.5 Sonnet
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Claude 4.5 SonnetModel Category=Proprietary Models, Data Type=In-house2026.05 | 42.9 | — | 58.1 | — | |
| RoTS-32BModel Category=Open-Weights Models (Larger Size), Data Type=Open-source2026.05 | 42.8 | 33.8 | 47.4 | — | |
| Qwen3-VL-PlusModel Category=Proprietary Models, Data Type=In-house2026.05 | 33.1 | 24.5 | 35.2 | — | |
| Qwen3-VL-FlashModel Category=Proprietary Models, Data Type=In-house2026.05 | 32.1 | 22.1 | 41.6 | — | |
| Doubao-1.5-ThinkingModel Category=Proprietary Models, Data Type=In-house2026.05 | 31.9 | — | 40 | — | |
| RoTS-7BModel Category=Open-Weights Models (Smaller Size), Data Type=Open-source2026.05 | 31.7 | 26.3 | 36.3 | — | |
| OpenCUA-32BModel Category=Open-Weights Models (Larger Size), Data Type=Open-source2026.05 | 29.7 | 15.5 | 34.1 | — | |
| Qwen3-VL-8B-ThinkingModel Category=Open-Weights Models (Smaller Size), Data Type=In-house2026.05 | 29.2 | 21.6 | 33.9 | — | |
| Qwen3-VL-32B-ThinkingModel Category=Open-Weights Models (Larger Size), Data Type=In-house2026.05 | 28.1 | 21.1 | 41 | — | |
| GUI-OWL-7BModel Category=Open-Weights Models (Smaller Size), Data Type=In-house2026.05 | 27.1 | 14.7 | 29.4 | — | |
| OpenAI CUAModel Category=Proprietary Models, Data Type=In-house2026.05 | 26 | — | 31.3 | — | |
| UI-TARS-1.5-7BModel Category=Open-Weights Models (Smaller Size), Data Type=In-house2026.05 | 24.5 | 9.5 | 27.3 | — | |
| OpenCUA-7BModel Category=Open-Weights Models (Smaller Size), Data Type=Open-source2026.05 | 24.3 | 12.5 | 28.2 | — | |
| UI-TARS-72B-DPOModel Category=Open-Weights Models (Larger Size), Data Type=In-house2026.05 | 24 | 11 | 25.8 | — | |
| Qwen2.5-VL-72BModel Category=Open-Weights Models (Larger Size), Data Type=In-house2026.05 | 4.4 | 1.1 | 5 | — | |
| Qwen2.5-VL-32BModel Category=Open-Weights Models (Larger Size), Data Type=In-house2026.05 | 3 | 0.7 | 3.9 | — | |
| CogAgentbase_agent=CogAgent2026.06 | — | — | — | 8.9 | |
| CogAgent + VisCriticbase_agent=CogAgent, critic_module=VisCritic2026.06 | — | — | — | 10.6 | |
| Qwen2.5-VL Agentbase_agent=Qwen2.5-VL Agent2026.06 | — | — | — | 14.2 | |
| Qwen2.5-VL Agent + GUI-Critic-R1base_agent=Qwen2.5-VL Agent, critic_module=GUI-Critic-R12026.06 | — | — | — | 17.4 | |
| Qwen2.5-VL Agent + GUI-PRAbase_agent=Qwen2.5-VL Agent, critic_module=GUI-PRA2026.06 | — | — | — | 16.3 | |
| Qwen2.5-VL Agent + GuidNavbase_agent=Qwen2.5-VL Agent, critic_module=GuidNav2026.06 | — | — | — | 17 | |
| Qwen2.5-VL Agent + VisCriticbase_agent=Qwen2.5-VL Agent, critic_module=VisCritic2026.06 | — | — | — | 17.1 | |
| SeeClickbase_agent=SeeClick2026.06 | — | — | — | 6.8 | |
| SeeClick + BacktrackAgentbase_agent=SeeClick, critic_module=BacktrackAgent2026.06 | — | — | — | 9 | |
| SeeClick + GUI-Critic-R1base_agent=SeeClick, critic_module=GUI-Critic-R12026.06 | — | — | — | 9.3 | |
| SeeClick + GUI-PRAbase_agent=SeeClick, critic_module=GUI-PRA2026.06 | — | — | — | 8.2 | |
| SeeClick + VisCriticbase_agent=SeeClick, critic_module=VisCritic2026.06 | — | — | — | 9.5 | |
| ShowUIbase_agent=ShowUI2026.06 | — | — | — | 10.3 | |
| ShowUI + GUI-PRAbase_agent=ShowUI, critic_module=GUI-PRA2026.06 | — | — | — | 12 | |
| ShowUI + VisCriticbase_agent=ShowUI, critic_module=VisCritic2026.06 | — | — | — | 12.8 |