List your company

Embodied task planning on BEHAVIOR-1K B-100 1.0

97.5SP%Gemini-3.1-Pro
67.8675.55583.2590.945Jun 30, 2026

Evaluation results

MethodLinks
Gemini-3.1-ProPrompt style=Guided extended-BDDL2026.0697.597.599.190
GPT-5.4Prompt style=Guided extended-BDDL2026.06979799.21
D-SFT+DAPO+Short-RLSize=8B, Prompt style=Guided extended-BDDL, Decoding seeds=32026.0695.295.599.321.5
Gemma-4-31B-ITSize=31B, Prompt style=Guided extended-BDDL2026.0694.596.599.212
D-SFT+DAPOSize=8B, Prompt style=Guided extended-BDDL, Decoding seeds=32026.0694.395.798.672
D-SFT+DAPO+Short-RL+GroupAdapt (τ=0.5)Size=8B, Prompt style=Guided extended-BDDL, Decoding seeds=3, τ=0.52026.069495.299.222.2
Kimi-K2.6Size=1T, Prompt style=Guided extended-BDDL2026.069397.599.364.5
GLM-5.1Size=754B, Prompt style=Guided extended-BDDL2026.069396.598.45.5
Qwen3.6-27BSize=27B, Prompt style=Guided extended-BDDL2026.0690.596.598.496.5
DeepSeek-V4-FlashSize=284B, Prompt style=Guided extended-BDDL2026.06909698.746.5
D-SFTSize=8B, Prompt style=Guided extended-BDDL, Decoding seeds=32026.068793.597.79.5
DeepSeek-V4-ProSize=1.6T, Prompt style=Guided extended-BDDL2026.0686.595.598.249.5
Qwen3.6-35B-A3BSize=35B, Prompt style=Guided extended-BDDL2026.06839496.6215.5
Qwen3.5-122B-A10BSize=122B, Prompt style=Guided extended-BDDL2026.0682.59396.9313.5
Qwen3.5-27BSize=27B, Prompt style=Guided extended-BDDL2026.068092.594.9118.5
Qwen3-8BSize=8B, Prompt style=Guided extended-BDDL2026.06728795.1723
Qwen3.5-35B-A3BSize=35B, Prompt style=Guided extended-BDDL2026.066982.586.8123.5