results/fundamental_nlp_tasks/zero_shot/qnli.csv

Model,Accuracy
Qwen2-7B-Instruct,0.8154859967051071
Meta-Llama-3.1-8B-Instruct,0.5777045579352005
Qwen2_5_32B_Instruct,0.9062786015010068
Qwen2_5_7B_Instruct,0.8652754896576972
Qwen2_5_1_5B_Instruct,0.6148636280431997
Qwen2-72B-Instruct,0.8887058392824455
Meta-Llama-3-8B-Instruct,0.6025993044114956
Meta-Llama-3.1-70B-Instruct,0.9026176093721399
Qwen2_5_3B_Instruct,0.7645982061138569
SeaLLMs-v3-7B-Chat,0.7159070107999268
Qwen2_5_72B_Instruct,0.9082921471718836
gemma-2-9b-it,0.9070107999267801
Meta-Llama-3-70B-Instruct,0.876807614863628
Qwen2_5_14B_Instruct,0.9079260479589969
gemma2-9b-cpt-sea-lionv3-instruct,0.9055464030752334
gemma-2-2b-it,0.7792421746293245
llama3-8b-cpt-sea-lionv2-instruct,0.6101043382756727
cross_openhermes_llama3_8b_12288_inst,0.8282994691561413
Qwen2_5_0_5B_Instruct,0.5464030752333883
GPT4o_0513,0.9304411495515285