List your company

Multimodal app-use reasoning on AppWorld

0.05CostStudent (ZS)
0.0120.26850.5250.7815Dec 2, 2025

Evaluation results

MethodLinks
Student (ZS)Model=Llama-3.3-70B, Zero-shot=true2025.120.0511
Student (ZS)Model=GPT-4.1-mini, Zero-shot=true2025.120.0928
Student (IC)Model=Llama-3.3-70B, In-Context Distillation=true2025.120.132
Student (IC)Model=GPT-4.1-mini, In-Context Distillation=true2025.120.1555
Student (IC+Cascade)Model=Llama-3.3-70B, In-Context Distillation=true, Self-Consistency Cascade=true2025.120.1944
Student (IC+Cascade)Model=GPT-4.1-mini, In-Context Distillation=true, Self-Consistency Cascade=true2025.120.2966
TeacherModel=Sonnet 4.52025.12183