List your company

Web Agent Tasks on Mind2Web Cross-Domain

55.7Ele.AccMagma-8B
-0.04414.42828.943.372Jan 17, 2024Jun 10, 2024Nov 2, 2024Mar 27, 2025Aug 19, 2025Jan 11, 2026Jun 6, 2026

Evaluation results

MethodLinks
Magma-8BBackbone=LLaMA3 [92], DoM Tree=true2025.0255.780.647.3
OmniParser2024.1145.585.742
GPT-4V-OmniParserBackbone=GPT-4V [99], DoM Tree=true, Image=true2025.0245.585.742
SKILL.nbZero-shot=true2026.0644.94639.7
SeeAct (GPT-4V)Backbone=GPT-4V [99], Image=true2025.0242.469.336.8
MindActw/o HTML=false2024.0142.166.539.6
MindActrequired HTML text inputs=true2024.1142.166.539.6
AWMonlineZero-shot=true2026.0640.936.335.5
ReasoningBankZero-shot=true2026.0640.641.336.6
Qwen2-UIXBackbone=Qwen2 [124]2025.0240.4—34.9
ShowUIFT?=true2024.1139.486.835.2
ShowUI †FT?=true, Action history only=true2024.1138.985.334.1
GPT-4w/o HTML=false2024.0137.146.526.4
GPT-4close-source=true2024.1137.146.526.4
GPT-4-MindActBackbone=GPT-4 [98], Image=true2025.0237.146.526.4
Qwen2-VL-2BFT?=true2024.1136.381.830.7
CodeActZero-shot=true2026.0635.837.931.9
CogAgentBackbone=CogVLM [118]2025.0233.1—28.5
ShowUI-ZSFT?=false2024.1124.483.921.4
DAVELanguage Model Backbone=Llama-3.2-3B-Instruct2025.1223.9—19.1
SeeClickw/o HTML=true2024.0123.284.820.8
SeeClickFT?=true2024.1123.284.820.8
SeeClickBackbone=Qwen-VL [3]2025.0223.284.820.8
GPT-3.5-Turbow/o HTML=false2024.0121.652.818.6
SeeAct (Gemini-Pro)Backbone=Gemini-Pro [36], Image=true2025.0220.764.318
CogAgentFT?=true2024.1120.64215.5
DolphinLanguage Model Backbone=Llama-3.2-3B-Instruct2025.1219.3—14.5
MiniCPM-V-GUIBackbone=MiniCPM-V [128], DoM Tree=true2025.0217.974.517.6
MAELanguage Model Backbone=Llama-3.2-3B-Instruct2025.1215.5—11.6
MindAct (gen)w/o HTML=false2024.0114.244.711.9
Fuyu-8B-GUIBackbone=Fuyu-8B [4], DoM Tree=true2025.0214.283.111.7
Qwen-VLw/o HTML=true2024.0114.184.312
Qwen-VLFT?=true2024.1114.184.312
Qwen-VLBackbone=Qwen-VL [3]2025.0214.184.312
SigLIP 2Language Model Backbone=Llama-3.2-3B-Instruct2025.1212.8—9.7
Pix2StructLanguage Model Backbone=Llama-3.2-3B-Instruct2025.1210.8—7.5
DinoV2Language Model Backbone=Llama-3.2-3B-Instruct2025.129.5—7.2
AIMv2Language Model Backbone=Llama-3.2-3B-Instruct2025.128.8—6.1
MiniCPM-V+Backbone=MiniCPM-V [128], DoM Tree=true2025.026.581.45.2
Fuyu-8B+Backbone=Fuyu-8B [4], DoM Tree=true2025.023.6833
DiTLanguage Model Backbone=Llama-3.2-3B-Instruct2025.122.1—1.1
GPT-4VBackbone=GPT-4V [99], Image=true2025.02—23.7—