python evaluate.py \
    --answer_file_list "path to answers of model 1" "path to answers of model 2" \
    --prompt_file "path to prompt file" \
    --reviewer_file "path to reviewer file" \
    --output_folder "path to output folder" \
    --openai_key "your openai key" \
    --model "gpt-4" \
    --num_workers 8 \
    --max_tokens 512 \