🔬 LLM Finetuning Arena
Comparing Finetuned vs. Base Models on Specialized Tasks
1. Select Domain
Math
Bio
2. Question Prompt (Editable)
A waiter had some customers. After 3 customers left, he still had 5 customers. Then he got 99 new customers. How many customers did the waiter have initially?
Load Random Question 🔄
3. Select Model 1 (Left)
4. Select Model 2 (Right)
🚀 Run Comparison
Show Ground Truth Answer