Benchmark Buddy

By Cavit Erginsoy

AI assistant for benchmarking community-finetuned LLMs, offering tailored questions in six areas and analysis.

Start using Benchmark Buddy on your ChatGPT

• public
• reportable

• Give me two questions for technical explanation testing in LLMs.
• What questions should I ask for specific general inquiry in models like LLama 2?
• I need coding questions for a Mistral 7B test.
• How would you grade this LLM response for creative writing?