results/fundamental_nlp_tasks/zero_shot/cola.csv

Model,Accuracy
Qwen2-7B-Instruct,0.7871524448705657
Meta-Llama-3.1-8B-Instruct,0.6519654841802492
llama3-8b-cpt-sea-lionv2.1-instruct,0.613614573346117
Qwen2_5_32B_Instruct,0.8427612655800575
Qwen2_5_7B_Instruct,0.7909875359539789
Qwen2_5_1_5B_Instruct,0.7497603068072867
Qwen2-72B-Instruct,0.8341323106423778
Sailor2-8B-Chat,0.7900287631831256
Meta-Llama-3-8B-Instruct,0.6548418024928092
Meta-Llama-3.1-70B-Instruct,0.850431447746884
Qwen2_5_3B_Instruct,0.6644295302013423
llama3.1-70b-cpt-sea-lionv3-instruct,0.8485139022051774
SeaLLMs-v3-7B-Chat,0.785234899328859
Qwen2_5_72B_Instruct,0.8571428571428571
meralion-merged-llama3-8b-sg-inst-avg-diff,0.6174496644295302
gemma-2-9b-it,0.7938638542665388
llama3.1-8b-cpt-sea-lionv3-instruct,0.7698945349952061
Meta-Llama-3-70B-Instruct,0.835091083413231
Qwen2_5_14B_Instruct,0.8063279002876318
gemma2-9b-cpt-sea-lionv3-instruct,0.825503355704698
gemma-2-2b-it,0.6749760306807286
llama3-8b-cpt-sea-lionv2-instruct,0.6078619367209971
cross_openhermes_llama3_8b_12288_inst,0.8207094918504314
Qwen2_5_0_5B_Instruct,0.6116970278044104
GPT4o_0513,0.8398849472674976