results/fundamental_nlp_tasks/zero_shot/mnli.csv

Model,Accuracy
Qwen2-7B-Instruct,0.7295
Meta-Llama-3.1-8B-Instruct,0.5295
llama3-8b-cpt-sea-lionv2.1-instruct,0.5775
Qwen2_5_32B_Instruct,0.8715
Qwen2_5_7B_Instruct,0.8105
Qwen2_5_1_5B_Instruct,0.6045
Qwen2-72B-Instruct,0.7925
Sailor2-8B-Chat,0.664
Meta-Llama-3-8B-Instruct,0.546
Meta-Llama-3.1-70B-Instruct,0.7015
Qwen2_5_3B_Instruct,0.7465
llama3.1-70b-cpt-sea-lionv3-instruct,0.736
SeaLLMs-v3-7B-Chat,0.653
Qwen2_5_72B_Instruct,0.8445
meralion-merged-llama3-8b-sg-inst-avg-diff,0.5375
gemma-2-9b-it,0.716
Meta-Llama-3-70B-Instruct,0.6709421285692472
Qwen2_5_14B_Instruct,0.818
gemma2-9b-cpt-sea-lionv3-instruct,0.7445
gemma-2-2b-it,0.6185
llama3-8b-cpt-sea-lionv2-instruct,0.5765
cross_openhermes_llama3_8b_12288_inst,0.6485
Qwen2_5_0_5B_Instruct,0.5095
GPT4o_0513,0.8335