Dashboard Overview

Real-time insights into your LLM A/B testing experiments

4
Total Experiments
2
Active Experiments
17756
Total Users
7
Models Tested
Total Interactions

153535

Completed Experiments

2

Top Performing Model
Claude-3-Opus
Recent Experiments View All
Experiment Name Status Users Primary Metric Action
GPT-4 vs Claude-3 Code Generation Completed 4521 response_quality_score View
Llama-3 vs Mixtral Q&A Completed 7834 converted View
GPT-3.5 vs GPT-4 Cost-Quality Tradeoff Running 3245 response_quality_score View
Gemini-1.5 vs GPT-4 Summarization Running 2156 converted View
Model Performance Compare
Experiment Activity (30 Days)