33 lines (23 loc) · 1.09 KB

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

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

Technologies Used

Threadexecutor
LangChain
HuggingFace
Streamlit

Output screenshot