results/general_reasoning/zero_shot/zbench.csv

Model,Accuracy
Qwen2-7B-Instruct,0.7272727272727273
Meta-Llama-3.1-8B-Instruct,0.42424242424242425
llama3-8b-cpt-sea-lionv2.1-instruct,0.2727272727272727
Gemma-2-9b-it-sg-ultrachat-sft,0.36363636363636365
Qwen2_5_32B_Instruct,0.6060606060606061
Qwen2_5_7B_Instruct,0.6666666666666666
Qwen2_5_1_5B_Instruct,0.42424242424242425
Qwen2-72B-Instruct,0.5757575757575758
MERALiON-LLaMA-3-8B-Chat,0.42424242424242425
Meta-Llama-3-8B-Instruct,0.3333333333333333
Meta-Llama-3.1-70B-Instruct,0.48484848484848486
Qwen2_5_3B_Instruct,0.5757575757575758
SeaLLMs-v3-7B-Chat,0.5454545454545454
Qwen2_5_72B_Instruct,0.696969696969697
gemma-2-9b-it,0.48484848484848486
Meta-Llama-3-70B-Instruct,0.5151515151515151
Qwen2_5_14B_Instruct,0.6666666666666666
gemma2-9b-cpt-sea-lionv3-instruct,0.42424242424242425
gemma-2-2b-it,0.24242424242424243
llama3-8b-cpt-sea-lionv2-instruct,0.30303030303030304
Qwen2_5_0_5B_Instruct,0.36363636363636365
GPT4o_0513,0.696969696969697