results/cultural_reasoning/zero_shot/ph_eval.csv

Model,Accuracy
Qwen2-7B-Instruct,0.52
Meta-Llama-3.1-8B-Instruct,0.6
llama3-8b-cpt-sea-lionv2.1-instruct,0.56
Qwen2_5_32B_Instruct,0.7
Qwen2_5_7B_Instruct,0.55
Qwen2_5_1_5B_Instruct,0.37
Qwen2-72B-Instruct,0.62
Meta-Llama-3-8B-Instruct,0.58
Meta-Llama-3.1-70B-Instruct,0.68
Qwen2_5_3B_Instruct,0.4
SeaLLMs-v3-7B-Chat,0.47
Qwen2_5_72B_Instruct,0.72
gemma-2-9b-it,0.58
Meta-Llama-3-70B-Instruct,0.63
Qwen2_5_14B_Instruct,0.6
gemma2-9b-cpt-sea-lionv3-instruct,0.59
gemma-2-2b-it,0.4
llama3-8b-cpt-sea-lionv2-instruct,0.56
cross_openhermes_llama3_8b_12288_inst,0.52
Qwen2_5_0_5B_Instruct,0.27
GPT4o_0513,0.77