results/general_reasoning/zero_shot/cmmlu.csv

Model,Accuracy
Qwen2-7B-Instruct,0.7727508202383008
Meta-Llama-3.1-8B-Instruct,0.5246934898981178
Gemma-2-9b-it-sg-ultrachat-sft,0.5615610429977551
Qwen2_5_32B_Instruct,0.8273182524607149
Qwen2_5_7B_Instruct,0.7486617164565705
Qwen2_5_1_5B_Instruct,0.5975651873596961
Qwen2-72B-Instruct,0.8293904334311863
MERALiON-LLaMA-3-8B-Chat,0.48877568640994645
Meta-Llama-3-8B-Instruct,0.4839405974788465
Meta-Llama-3.1-70B-Instruct,0.6814885166637886
Qwen2_5_3B_Instruct,0.6621481609393887
SeaLLMs-v3-7B-Chat,0.7684337765498187
Qwen2_5_72B_Instruct,0.8343982041098256
gemma-2-9b-it,0.5700224486271801
Meta-Llama-3-70B-Instruct,0.6494560524952513
Qwen2_5_14B_Instruct,0.7807805214988776
gemma2-9b-cpt-sea-lionv3-instruct,0.5796062856156105
gemma-2-2b-it,0.4412882058366431
llama3-8b-cpt-sea-lionv2-instruct,0.48929373165256435
Qwen2_5_0_5B_Instruct,0.42056639613192887
GPT4o_0513,0.7414954239336902