List your company

Reasoning Efficiency on ScienceWorld (Seen)

83.16Success Rate (%)BPO
55.641662.785869.9377.0742Aug 5, 2025

Evaluation results

MethodLinks
BPOSize=8B2025.0883.16112
Qwen-3-ThinkingSize=8B2025.0857.45763
Deepseek-R1Size=671B2025.0856.7620