results/fundamental_nlp_tasks/zero_shot/wnli.csv

Model,Accuracy
Qwen2-7B-Instruct,0.7183098591549296
Meta-Llama-3.1-8B-Instruct,0.6197183098591549
llama3-8b-cpt-sea-lionv2.1-instruct,0.5915492957746479
Qwen2_5_32B_Instruct,0.8732394366197183
Qwen2_5_7B_Instruct,0.7605633802816901
Qwen2_5_1_5B_Instruct,0.4647887323943662
Qwen2-72B-Instruct,0.8873239436619719
Sailor2-8B-Chat,0.5492957746478874
Meta-Llama-3-8B-Instruct,0.4788732394366197
Meta-Llama-3.1-70B-Instruct,0.8450704225352113
Qwen2_5_3B_Instruct,0.647887323943662
llama3.1-70b-cpt-sea-lionv3-instruct,0.8591549295774648
SeaLLMs-v3-7B-Chat,0.5915492957746479
Qwen2_5_72B_Instruct,0.8169014084507042
meralion-merged-llama3-8b-sg-inst-avg-diff,0.5492957746478874
gemma-2-9b-it,0.7746478873239436
llama3.1-8b-cpt-sea-lionv3-instruct,0.7323943661971831
Meta-Llama-3-70B-Instruct,0.7887323943661971
Qwen2_5_14B_Instruct,0.8309859154929577
gemma2-9b-cpt-sea-lionv3-instruct,0.7605633802816901
gemma-2-2b-it,0.43661971830985913
llama3-8b-cpt-sea-lionv2-instruct,0.5774647887323944
cross_openhermes_llama3_8b_12288_inst,0.5211267605633803
Qwen2_5_0_5B_Instruct,0.43661971830985913
GPT4o_0513,0.9295774647887324