List your company

Embodied Planning on Causal-Plan-Bench in-domain

45.28Overall Success RateCausal Planner
29.52433.614537.70541.7955Jun 1, 2026

Evaluation results

MethodLinks
Causal PlannerScale=8B, Category=Embodied Specific Models2026.0645.284845.3342.645.17
Gemini 3 ProCategory=Closed-Source Models2026.0638.1840.673637.1338.9
RynnBrainScale=8B, Category=Embodied Specific Models2026.0637.4343.3334.3333.9738.07
Seed2.0 ProCategory=Closed-Source Models2026.0637.224237.3331.9337.6
GPT-5.4Category=Closed-Source Models2026.0636.9939.673633.7338.57
RoboBrain-2.5Scale=8B, Category=Embodied Specific Models2026.0636.574432.673435.6
MiMo-EmbodiedScale=7B, Category=Embodied Specific Models2026.0634.5338.3333.6730.935.23
Cosmos-Reason2Scale=8B, Category=Embodied Specific Models2026.0634.484032.6732.0333.2
Kimi K2.5Scale=1T, Category=Open-Source Models2026.0633.6633.6733.3331.735.93
Gemini 2.5 ProCategory=Closed-Source Models2026.0633.483631.3331.5735.03
Qwen3-VLScale=8B, Category=Open-Source Models2026.0633.2338.673328.133.13
InternVL3.5Scale=8B, Category=Open-Source Models2026.0632.7838.3331.6728.9332.17
GPT-4oCategory=Closed-Source Models2026.0632.5835.3330.3332.632.07
RoboBrain-2.0Scale=7B, Category=Embodied Specific Models2026.0631.263628.6727.532.87
Qwen2.5-VLScale=7B, Category=Open-Source Models2026.0630.1335.672826.0730.77
Cosmos-Reason1Scale=7B, Category=Embodied Specific Models2026.0630.1334.3328.6727.0730.47