results/fundamental_nlp_tasks/zero_shot/c3.csv

Model,Accuracy
Qwen2-7B-Instruct,0.9244577412116679
Meta-Llama-3.1-8B-Instruct,0.8672400897531788
llama3-8b-cpt-sea-lionv2.1-instruct,0.8676140613313388
Qwen2_5_32B_Instruct,0.9603590127150337
Qwen2_5_7B_Instruct,0.9121166791323859
Qwen2_5_1_5B_Instruct,0.793941660433807
Qwen2-72B-Instruct,0.9611069558713538
Meta-Llama-3-8B-Instruct,0.8515332834704562
Meta-Llama-3.1-70B-Instruct,0.9603590127150337
Qwen2_5_3B_Instruct,0.8668661181750187
SeaLLMs-v3-7B-Chat,0.9143605086013463
Qwen2_5_72B_Instruct,0.9596110695587136
gemma-2-9b-it,0.9222139117427075
Meta-Llama-3-70B-Instruct,0.9521316379955124
Qwen2_5_14B_Instruct,0.9502617801047121
Meta-Llama-3.1-70B,0.7786088257292446
gemma2-9b-cpt-sea-lionv3-instruct,0.9255796559461481
gemma-2-2b-it,0.7700074794315632
llama3-8b-cpt-sea-lionv2-instruct,0.8672400897531788
cross_openhermes_llama3_8b_12288_inst,0.8485415108451758
Qwen2_5_0_5B_Instruct,0.612939416604338
GPT4o_0513,0.9648466716529543