testcase-data/eval_all_wrong_code.sh

cd /home/luoxianzhen/yang/eval_wrong_code

# 定义算法列表
# test_als=("lcb" "ht" "algo" "crux" "predo")
test_als=("lcb")

# version=("v1" "v2" "v3" "v4" "v5")

version=("v3" "v4" "v5")

# 定义模型列表 
model_name_list=(
    "claude-sonnet-4-20250514-thinking"
    # "deepseek-v3"
    # "qwen3-nothink"
    # "claude4"
    # "gpt-4o"
    # "qwen-coder-plus"
    # "Qwen2.5-7B-Instruct"
    # "Qwen2.5-14B-Instruct"
    # "Qwen2.5-32B-Instruct"
    # "Qwen2.5-Coder-7B-Instruct"
    # "Qwen2.5-Coder-14B-Instruct"
    # "Qwen2.5-Coder-32B-Instruct"
)

# 双层循环执行
for model in "${model_name_list[@]}"; do
    for alg in "${test_als[@]}"; do
        for ver in in "${version[@]}"; do
            echo "Running testcase_alg=$alg model_name=$model"
            python parallel_exe_all_wrong_code.py \
                --testcase_alg "$alg" \
                --model_name "$model" \
                --version "$ver"
        done
    done
done