List your company
ResearchFormerly WizWand

Vision-Language Navigation on R2R-Goal (val unseen)

36Success Rate (SR)Human Annotation
16.2421.3726.531.63Aug 13, 2025
Updated 6mo ago

Evaluation results

MethodLinks
Human AnnotationInstruction Generator=Human Annotation, Evaluation Navigator Agent=ETPNav2025.083628
Human AnnotationInstruction Generator=Human Annotation, Evaluation Navigator Agent=BEVBert2025.083427
Anole-7B + InterleavedInstruction Generator=Anole-7B + Interleaved, Evaluation Navigator Agent=ETPNav2025.083425
Anole-7B + InterleavedInstruction Generator=Anole-7B + Interleaved, Evaluation Navigator Agent=BEVBert2025.083325
Anole-7B + One-passInstruction Generator=Anole-7B + One-pass, Evaluation Navigator Agent=ETPNav2025.083120
C-InstructorInstruction Generator=C-Instructor, Evaluation Navigator Agent=ETPNav2025.082919
Anole-7B + One-passInstruction Generator=Anole-7B + One-pass, Evaluation Navigator Agent=BEVBert2025.082921
C-InstructorInstruction Generator=C-Instructor, Evaluation Navigator Agent=BEVBert2025.082718
Gemini 3.0Instruction Generator=Gemini 3.0, Evaluation Navigator Agent=ETPNav2025.082718
Claude 4 OpusInstruction Generator=Claude 4 Opus, Evaluation Navigator Agent=ETPNav2025.082616
GPT-4o + CoTInstruction Generator=GPT-4o + CoT, Evaluation Navigator Agent=ETPNav2025.082517
Gemini 3.0Instruction Generator=Gemini 3.0, Evaluation Navigator Agent=BEVBert2025.082514
Claude 4 OpusInstruction Generator=Claude 4 Opus, Evaluation Navigator Agent=BEVBert2025.082517
Anole-7B + CoTInstruction Generator=Anole-7B + CoT, Evaluation Navigator Agent=ETPNav2025.082516
GPT-4o + CoTInstruction Generator=GPT-4o + CoT, Evaluation Navigator Agent=BEVBert2025.082417
GPT-4oInstruction Generator=GPT-4o, Evaluation Navigator Agent=ETPNav2025.082316
Anole-7B + CoTInstruction Generator=Anole-7B + CoT, Evaluation Navigator Agent=BEVBert2025.082315
GPT-4oInstruction Generator=GPT-4o, Evaluation Navigator Agent=BEVBert2025.082214
Anole-7B + DirectInstruction Generator=Anole-7B + Direct, Evaluation Navigator Agent=ETPNav2025.082014
LANAInstruction Generator=LANA, Evaluation Navigator Agent=ETPNav2025.081811
Anole-7B + DirectInstruction Generator=Anole-7B + Direct, Evaluation Navigator Agent=BEVBert2025.081813
LANAInstruction Generator=LANA, Evaluation Navigator Agent=BEVBert2025.081712