List your company

Web Navigation and Automation on WorkArena Held-out Goals (test)

53.8Success Rateo1-Mini
2.52815.83929.1542.461Jul 5, 2025

Evaluation results

MethodLinks
o1-MiniBackbone Model=o1-Mini2025.0753.8
Claude-3.5-SonnetBackbone Model=Claude-3.5-Sonnet2025.0752.5
GPT-4oBackbone Model=GPT-4o2025.0742.1
Llama-3.1-405B-InstructBackbone Model=Llama-3.1-405B2025.0739.2
Llama-3.3-70B Instruct (Teacher)Backbone Model=Llama-3.3-70B, Model Role=Teacher2025.0736
Llama-3.1-8B SFT+RL (Ours)Backbone Model=Llama-3.1-8B, Training Protocol=SFT+RL2025.0735.4
Qwen-2.5-72B Instruct (Teacher)Backbone Model=Qwen-2.5-72B, Model Role=Teacher2025.0733.3
Qwen-2.5-7B SFT+RL (Ours)Backbone Model=Qwen-2.5-7B, Training Protocol=SFT+RL2025.0732.5
Llama-3.1-8B SFT (Ours)Backbone Model=Llama-3.1-8B, Training Protocol=SFT2025.0728.4
GPT-4o-MiniBackbone Model=GPT-4o-Mini2025.0727.1
Llama-3.1-70B-InstructBackbone Model=Llama-3.1-70B2025.0725
Qwen-2.5-7B SFT (Ours)Backbone Model=Qwen-2.5-7B, Training Protocol=SFT2025.0725
Llama-3.1-8B Instruct (Student)Backbone Model=Llama-3.1-8B, Model Role=Student2025.078.3
Llama-3.1-8B RL (Ours)Backbone Model=Llama-3.1-8B, Training Protocol=RL2025.078
Qwen-2.5-7B Instruct (Student)Backbone Model=Qwen-2.5-7B, Model Role=Student2025.075.2
Qwen-2.5-7B RL (Ours)Backbone Model=Qwen-2.5-7B, Training Protocol=RL2025.074.5