results/cultural_reasoning/zero_shot/cn_eval.csv

Model,Accuracy
Qwen2-7B-Instruct,0.8285714285714286
Meta-Llama-3.1-8B-Instruct,0.4857142857142857
llama3-8b-cpt-sea-lionv2.1-instruct,0.5047619047619047
Qwen2_5_32B_Instruct,0.8476190476190476
Qwen2_5_7B_Instruct,0.8
Qwen2_5_1_5B_Instruct,0.5523809523809524
Qwen2-72B-Instruct,0.8285714285714286
Meta-Llama-3-8B-Instruct,0.4666666666666667
Meta-Llama-3.1-70B-Instruct,0.5428571428571428
Qwen2_5_3B_Instruct,0.7142857142857143
SeaLLMs-v3-7B-Chat,0.819047619047619
Qwen2_5_72B_Instruct,0.8761904761904762
gemma-2-9b-it,0.580952380952381
Meta-Llama-3-70B-Instruct,0.5333333333333333
Qwen2_5_14B_Instruct,0.8285714285714286
gemma2-9b-cpt-sea-lionv3-instruct,0.5904761904761905
gemma-2-2b-it,0.3619047619047619
llama3-8b-cpt-sea-lionv2-instruct,0.49523809523809526
cross_openhermes_llama3_8b_12288_inst,0.5523809523809524
Qwen2_5_0_5B_Instruct,0.3619047619047619
GPT4o_0513,0.8095238095238095