List your company
ResearchFormerly WizWand

Long-horizon procedural planning on EgoPlan-Bench All

58.72Success RatePlanAgent + Mem.
26.32434.734543.14551.5555Mar 9, 2026
Updated 8mo ago

Evaluation results

MethodLinks
PlanAgent + Mem.Base Model=Qwen3-VL-8B, Instruction Tuning=true, Preference Alignment=true2026.0358.72
GPT-5.1Base Model=-, Instruction Tuning=false, Preference Alignment=false2026.0354.78
PlanAgent + Mem.Base Model=Qwen3-VL-8B, Instruction Tuning=true, Preference Alignment=false2026.0353.29
Video-LLaMABase Model=LLaMA2-Chat-7B, Instruction Tuning=true, Preference Alignment=true2026.0351.83
Video-LLaMABase Model=LLaMA2-Chat-7B, Instruction Tuning=true, Preference Alignment=false2026.0348.94
PlanAgent + Mem.Base Model=Qwen3-VL-8B, Instruction Tuning=false, Preference Alignment=false2026.0343.63
GPT-4VBase Model=-, Instruction Tuning=false, Preference Alignment=false2026.0337.98
PlanAgent (Ours)Base Model=Qwen3-VL-8B, Instruction Tuning=false, Preference Alignment=false2026.0335.81
Gemini-Pro-VisionBase Model=-, Instruction Tuning=false, Preference Alignment=false2026.0330.46
SEED-LLaMABase Model=LLaMA2-Chat-13B, Instruction Tuning=false, Preference Alignment=false2026.0329.93
Video-LLaMABase Model=LLaMA2-Chat-7B, Instruction Tuning=false, Preference Alignment=false2026.0328.58
Qwen-VL-ChatBase Model=Qwen-7B, Instruction Tuning=false, Preference Alignment=false2026.0327.69
DeepSeek-VL-ChatBase Model=DeepSeek-LLM-7B, Instruction Tuning=false, Preference Alignment=false2026.0327.57