Model-Comparison

Goal : Use 1 to 4 models simultaneously to get answer of reasoning questions and user can get idea which model is giving best possible answer.

Acess at https://comparepy-model.streamlit.app/

Avilable Models

1. "zai-org":"zai-org/GLM-4.7-Flash"
2. "deep-seek":"deepseek-ai/DeepSeek-V3.2"
3. "meta-llama":"meta-llama/Llama-3.1-8B-Instruct",
4. "OpenAI":"openai/gpt-oss-20b", "Qwen":"Qwen/Qwen3-8B",
5. "Mistral":"mistralai/Mistral-7B-Instruct-v0.2",
6. "Google" : "google/gemma-2-9b-it",
7. "Xiaomi" : "XiaomiMiMo/MiMo-V2-Flash",
8. "Nvidia" : "nvidia/OpenReasoning-Nemotron-7B",
9. "MiniMaxAi" : "MiniMaxAI/MiniMax-M2.1",
10. "moonshotai" : "moonshotai/Kimi-K2-Thinking",
11. "Stabilityai" : "stabilityai/ar-stablelm-2-base"

Technologies Used

• Threadexecutor
• LangChain
• HuggingFace
• Streamlit

Output screenshot