ResearchBenchmarksCross-domain demo-to-code on Combination Factor Medium-ComplexityFollow65Success Rate (SR)NESYCR18.230.3542.554.65Mar 19, 2026Evaluation ResultsMethodMethodLinksSuccess Rate (SR)Goal Completion (GC)Policy Deviation (PD)NESYCR2026.036583.336.6Statler2026.0352.582.564.42MoReVQA2026.034568.3348.49Critic-V2026.0337.569.175.93GPT4V-Robotics2026.033569.1732.38LLM-DM2026.0322.56080.56Demo2Code2026.032048.335.56