List your company

Embodied Planning on AlfWorld (out of distribution)

58.95AccuracyProCeedSFT
10.839623.329835.8248.3102Apr 2, 2026

Evaluation results

MethodLinks
ProCeedSFTBackbone=Qwen3-8B2026.0458.95
ProCeedRLBackbone=Qwen3-8B2026.0455.22
DAPOBackbone=Qwen3-8B2026.0453.24
RFTBackbone=Qwen3-8B2026.0450.25
Qwen3-8BBackbone=Qwen3-8B2026.0447.07
DAPOBackbone=Qwen3-1.7B2026.0424.12
ProCeedRLBackbone=Qwen3-1.7B2026.0423.33
Qwen3-1.7BBackbone=Qwen3-1.7B2026.0412.69