Home Quick Start Prompt Library Use Cases

LEARN / Quick Start Models SUPPORT / Troubleshoot FAQ MORE / Glossary What's New

DOCS / Security & Privacy Admin Guide MONITOR / Dashboard Governance & Audit Health Center MANAGE / Users Teams Model Catalog TOOLS / API Keys Response Comparison API Playground Guardrails SYSTEM / Console Settings

MODEL BUILD / Dataset Creation Model Training INTELLIGENCE / Document Intelligence AI Workspace Prompt Studio Meeting Assistant AUTOMATION / Agent Studio Scheduled Jobs Workflow Designer QUALITY / AI Eval Suite Chat Rooms

Basic Tier

Admin · Evaluation

Performance Benchmark

Measure inference latency, generation speed, and output-token throughput across installed models using your own test prompts.

Pro Tier & Above

Model benchmarking requires the hardware throughput of Mid or Advanced tier to produce meaningful latency comparisons.

Select Models

Choose up to 5 models to compare. Models must be loaded in Ollama.

Test Prompts

Add prompts to run against each model. Up to 10 prompts.

Max tokens:

Nexus One AI · Powered by Cezen · Basic Tier

Questions? support@cezentech.com · cezentech.com