List your company

multi-step operation sequence prediction on Android-In-The-Zoo

74.43PrecisionTeach VLM
3.044421.577240.1158.6428Jun 11, 2026

Evaluation results

MethodLinks
Teach VLM2026.0674.4373.8574.1425.56
Doubao-Seed-1.82026.0644.1335.5639.3955.87
Doubao-Seed-2.02026.0641.1436.0338.4258.86
Qwen3-VL-8B2026.0634.6225.729.565.38
GPT-4o2026.0619.1516.717.8480.85
Qwen3.5-9B2026.065.7913.278.0694.21