testcase-data/eval_algo.sh

cd /home/luoxianzhen/yang/eval_wrong_code

# 定义算法列表
# test_als=("lcb" "ht" "algo" "crux" "predo")
test_als=("algo")
# 定义模型列表 
model_name_list=(
    # "claude-sonnet-4-20250514-thinking"
    # "deepseek-v3"
    # "qwen3-235b-a22b"
    # "claude-sonnet-4-20250514"
    # "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 alg in "${test_als[@]}"; do
    for model in "${model_name_list[@]}"; do
        echo "Running testcase_alg=$alg model_name=$model"
        python parallel_exe_algo.py \
            --testcase_alg "$alg" \
            --model_name "$model"
    done
done