List your company
ResearchFormerly WizWand

Process-constrained task execution on FullHome (VirtualHome)

51.4Process Success RateTaskGround
-1.01612.59226.239.808May 18, 2026
Updated 5mo ago

Evaluation results

MethodLinks
TaskGroundModel=GPT-52026.0551.4
TaskGroundModel=GPT-52026.0546
TaskGroundModel=GPT-4.12026.0545.7
TaskGroundModel=DeepSeek-V4-Flash2026.0542.9
TaskGroundModel=MiMo-V2-Flash2026.0540
TaskGroundModel=Qwen3.5-9B2026.0540
TaskGroundModel=Gemini-2.5-Flash2026.0537.1
TaskGroundModel=GPT-4o2026.0537
TaskGroundModel=DeepSeek-V4-Flash2026.0536
TaskGroundModel=GPT-4o2026.0535.5
TaskGroundModel=Gemma-3-12B2026.0534.3
TaskGroundModel=GPT-4.12026.0534
NaiveModel=GPT-52026.0531.4
TaskGroundModel=Qwen3.5-9B2026.0529
NaiveModel=GPT-52026.0526
NaiveModel=DeepSeek-V4-Flash2026.0525.7
NaiveModel=GPT-4o2026.0523.3
TaskGroundModel=MiMo-V2-Flash2026.0523
TaskGroundModel=Gemini-2.5-Flash2026.0519
TaskGroundModel=Gemma-3-12B2026.0519
NaiveModel=GPT-4.12026.0517.1
NaiveModel=DeepSeek-V4-Flash2026.0515
NaiveModel=Qwen3.5-9B2026.0514.3
NaiveModel=MiMo-V2-Flash2026.0511.4
NaiveModel=Qwen3.5-9B2026.0510
NaiveModel=Gemini-2.5-Flash2026.055.7
NaiveModel=Gemma-3-12B2026.055.7
NaiveModel=GPT-4o2026.055
NaiveModel=GPT-4.12026.054
NaiveModel=Gemini-2.5-Flash2026.052
NaiveModel=MiMo-V2-Flash2026.051
NaiveModel=Gemma-3-12B2026.051