List your company

Question Answering on ARC Challenge (Accuracy and Sample Size)

90.3AccuracyGrACE-SC
85.72486.91288.189.288Sep 11, 2025

Evaluation results

MethodLinks
GrACE-SCBackbone=Qwen2.5, Sampling budget T=82025.0990.38
GrACE-ESBackbone=Qwen2.5, Sampling budget T=82025.0990.12.47
SCBackbone=Qwen2.5, Sampling budget T=82025.0989.58
ESCBackbone=Qwen2.5, Sampling budget T=82025.0989.34.32
ASCBackbone=Qwen2.5, Sampling budget T=82025.0988.72.23
GrACE-SCBackbone=Llama-3.1, Sampling budget T=82025.0987.28
GrACE-ESBackbone=Llama-3.1, Sampling budget T=82025.0987.22.14
SCBackbone=Llama-3.1, Sampling budget T=82025.0986.38
ESCBackbone=Llama-3.1, Sampling budget T=82025.0986.34.69
ASCBackbone=Llama-3.1, Sampling budget T=82025.0985.92.34