> This page is for version Dev.
> For other versions, use one of these documentation indexes:
> - 3.3.0 (default): https://docs.nvidia.com/vss/3.3.0/llms.txt
> - Dev: https://docs.nvidia.com/vss/dev/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/vss/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/vss/_mcp/server.

# Accuracy & Performance Benchmarks

This section provides official benchmark results for key Foundational Blueprints, Agents, and Deployment Profiles, detailing specific metrics used, evaluation datasets, and methodology for reproducibility.

## Accuracy

### Sparse4D Model Accuracy

Refer to the [KPI](/system-components/models/sparse4d-3d-multi-camera#kpi) section of the Sparse4D model page.

### Sparse4D Model Throughput & Latency

Refer to the [Real-Time Inference Throughput & Latency](/system-components/models/sparse4d-3d-multi-camera#real-time-inference-throughput-latency) section of the Sparse4D model page.

### Warehouse Blueprint 2D & 3D Latency

Refer to the [Warehouse Blueprint 2D Latency](/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/deployment-customization/2d-vision-ai-with-agents-profile#latency-measurements) and [Warehouse Blueprint 3D Latency](/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/deployment-customization/3d-vision-ai-profile#latency-measurements) to get the latency of the Warehouse Blueprints.

## Caveats

Accuracy can vary between synthetic and real-world scenes and with camera placement, calibration, and detection thresholds. Throughput and latency depend on GPU hardware, stream count, input resolution, and enabled services. Compare results using the same dataset, configuration, and measurement method.