results/fundamental_nlp_tasks/zero_shot/mrpc.csv

Model,Accuracy
Qwen2-7B-Instruct,0.7867647058823529
Meta-Llama-3.1-8B-Instruct,0.6740196078431373
llama3-8b-cpt-sea-lionv2.1-instruct,0.5808823529411765
Qwen2_5_32B_Instruct,0.7745098039215687
Qwen2_5_7B_Instruct,0.7058823529411765
Qwen2_5_1_5B_Instruct,0.6838235294117647
Qwen2-72B-Instruct,0.8063725490196079
Meta-Llama-3-8B-Instruct,0.678921568627451
Meta-Llama-3.1-70B-Instruct,0.7696078431372549
Qwen2_5_3B_Instruct,0.5661764705882353
SeaLLMs-v3-7B-Chat,0.7475490196078431
Qwen2_5_72B_Instruct,0.8014705882352942
gemma-2-9b-it,0.7401960784313726
Meta-Llama-3-70B-Instruct,0.7598039215686274
Qwen2_5_14B_Instruct,0.7794117647058824
gemma2-9b-cpt-sea-lionv3-instruct,0.7794117647058824
gemma-2-2b-it,0.7083333333333334
llama3-8b-cpt-sea-lionv2-instruct,0.5833333333333334
cross_openhermes_llama3_8b_12288_inst,0.6985294117647058
Qwen2_5_0_5B_Instruct,0.5759803921568627
GPT4o_0513,0.7377450980392157