List your company

Physical outcome and stability prediction on TraySim

79.8AccuracyLLMPhy
30.19243.07155.9568.829Nov 12, 2024

Evaluation results

MethodLinks
LLMPhyPhase 1=LLMPhy (Phi-4), Phase 2=GT2024.1179.8
LLMPhyPhase 1=LLMPhy (o1-mini), Phase 2=GT2024.1177.5
LLMPhyPhase 1=LLMPhy (Gemma3), Phase 2=GT2024.1177.3
CMA-ESPhase 1=CMA-ES, Phase 2=GT2024.1175.8
Best-of-KPhase 1=Best-of-K, Phase 2=GT2024.1172
GPT-4.1Phase 1=GT, Phase 2=GPT-4.12024.1168.3
LLMPhyPhase 1=LLMPhy (o3-mini), Phase 2=LLMPhy (GPT-4.1)2024.1166.3
LLMPhyPhase 1=LLMPhy (o1-mini), Phase 2=LLMPhy (GPT-4.1)2024.1166
GPT-4oPhase 1=GT, Phase 2=GPT-4o2024.1165.1
LLMPhyPhase 1=LLMPhy (o1-mini), Phase 2=LLMPhy (GPT-4o)2024.1162
CMA-ESPhase 1=CMA-ES, Phase 2=LLMPhy (GPT-4o)2024.1159.7
Bayes Opt.Phase 1=Bayes Opt., Phase 2=LLMPhy (GPT-4o)2024.1159.6
HumanPhase 1=Human, Phase 2=Human2024.1154.2
RandomPhase 1=Random, Phase 2=GT2024.1150.8
Intuitive PhysicsPhase 1=Intuitive Physics, Phase 2=GPT-4o2024.1132.1