results/fundamental_nlp_tasks/zero_shot/rte.csv

Model,Accuracy
Qwen2-7B-Instruct,0.8231046931407943
Meta-Llama-3.1-8B-Instruct,0.6389891696750902
llama3-8b-cpt-sea-lionv2.1-instruct,0.6859205776173285
Qwen2_5_32B_Instruct,0.9097472924187726
Qwen2_5_7B_Instruct,0.8592057761732852
Qwen2_5_1_5B_Instruct,0.703971119133574
Qwen2-72B-Instruct,0.8447653429602888
Sailor2-8B-Chat,0.8122743682310469
Meta-Llama-3-8B-Instruct,0.6173285198555957
Meta-Llama-3.1-70B-Instruct,0.8483754512635379
Qwen2_5_3B_Instruct,0.779783393501805
llama3.1-70b-cpt-sea-lionv3-instruct,0.8880866425992779
SeaLLMs-v3-7B-Chat,0.7870036101083032
Qwen2_5_72B_Instruct,0.9025270758122743
meralion-merged-llama3-8b-sg-inst-avg-diff,0.6606498194945848
gemma-2-9b-it,0.7472924187725631
llama3.1-8b-cpt-sea-lionv3-instruct,0.7833935018050542
Meta-Llama-3-70B-Instruct,0.8086642599277978
Qwen2_5_14B_Instruct,0.8664259927797834
gemma2-9b-cpt-sea-lionv3-instruct,0.8483754512635379
gemma-2-2b-it,0.7292418772563177
llama3-8b-cpt-sea-lionv2-instruct,0.6859205776173285
cross_openhermes_llama3_8b_12288_inst,0.8050541516245487
Qwen2_5_0_5B_Instruct,0.5992779783393501
GPT4o_0513,0.8700361010830325