results/cultural_reasoning/zero_shot/us_eval.csv

Model,Accuracy
Qwen2-7B-Instruct,0.7289719626168224
Meta-Llama-3.1-8B-Instruct,0.7289719626168224
llama3-8b-cpt-sea-lionv2.1-instruct,0.7102803738317757
Gemma-2-9b-it-sg-ultrachat-sft,0.794392523364486
Qwen2_5_32B_Instruct,0.8411214953271028
Qwen2_5_7B_Instruct,0.7663551401869159
Qwen2_5_1_5B_Instruct,0.5981308411214953
Qwen2-72B-Instruct,0.8785046728971962
cross_openhermes_llama3_8b_4096_inst,0.6448598130841121
Meta-Llama-3-8B-Instruct,0.7009345794392523
Meta-Llama-3.1-70B-Instruct,0.8411214953271028
Qwen2_5_3B_Instruct,0.6728971962616822
cross_openhermes_llama3_8b_16384_inst,0.7663551401869159
cross_openhermes_llama3_70b_4096_inst_2,0.8598130841121495
SeaLLMs-v3-7B-Chat,0.6915887850467289
Qwen2_5_72B_Instruct,0.8598130841121495
gemma-2-9b-it,0.8130841121495327
Meta-Llama-3-70B-Instruct,0.8691588785046729
llama-own-4096-2-sg-ultrachat-sft-eos-real,0.6635514018691588
Qwen2_5_14B_Instruct,0.822429906542056
sg_llama3_8192_8b,0.7009345794392523
gemma2-9b-cpt-sea-lionv3-instruct,0.8037383177570093
sg_llama3_70b_inst,0.8598130841121495
cross_openhermes_llama3_8b_2048_inst,0.7102803738317757
gemma-2-2b-it,0.6915887850467289
llama3-8b-cpt-sea-lionv2-instruct,0.7009345794392523
cross_openhermes_llama3_8b_12288_inst,0.7663551401869159
Qwen2_5_0_5B_Instruct,0.37383177570093457
GPT4o_0513,0.8691588785046729
cross_openhermes_llama3_8b_8192_inst,0.7383177570093458
cross_openhermes_llama3_70b_4096_inst,0.8317757009345794
cross_openhermes_llama3_8b_4096_2_inst,0.7289719626168224