results/general_reasoning/zero_shot/mmlu.csv

Model,Accuracy
Qwen2-7B-Instruct,0.672506256703611
Meta-Llama-3.1-8B-Instruct,0.6387558097962103
llama3-8b-cpt-sea-lionv2.1-instruct,0.6117268501966393
Qwen2_5_32B_Instruct,0.7996424740793707
Qwen2_5_7B_Instruct,0.6935287808366106
Qwen2_5_1_5B_Instruct,0.5646764390418305
Qwen2-72B-Instruct,0.7922774401144083
Sailor2-8B-Chat,0.6202359671076153
Meta-Llama-3-8B-Instruct,0.6005720414730068
MERaLiON-Llama-3-8B-Instruct,0.631748301751877
Meta-Llama-3.1-70B-Instruct,0.8058634250983197
Qwen2_5_3B_Instruct,0.6118698605648909
SeaLLMs-v3-7B-Chat,0.6670003575259207
Qwen2_5_72B_Instruct,0.8129424383267787
gemma-2-9b-it,0.7100464783696818
Meta-Llama-3-70B-Instruct,0.7649624597783339
Qwen2_5_14B_Instruct,0.7542366821594566
gemma2-9b-cpt-sea-lionv3-instruct,0.7079013228459063
gemma-2-2b-it,0.5706828745084018
llama3-8b-cpt-sea-lionv2-instruct,0.6130854486950303
Qwen2_5_0_5B_Instruct,0.461136932427601
GPT4o_0513,0.8308187343582409