List your company

Common Sense Reasoning on T4D

85.99AccuracyATAR
38.170850.58546375.4146Oct 3, 2025

Evaluation results

MethodLinks
ATARBase Model=Phi-42025.1085.99
ATARBase Model=Qwen3-30B2025.1085.56
ATARBase Model=Qwen3-4B2025.1071.56
ATARBase Model=Phi-4-mini2025.1049.47
ATARBase Model=Llama3.2-3B2025.1043.79
ATARBase Model=Llama3.1-8B2025.1040.01