How RTX PRO 6000 Blackwell’s scores are calculated

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

• [probe] https://developer.nvidia.com/llms.txt“PROBE llms.txt: HTTP 200 at https://developer.nvidia.com/llms.txt # NVIDIA Developer > Comprehensive developer portal for NVIDIA accelerated computing, AI, robotics, graphics, and simul”
• [probe] https://developer.nvidia.com/cuda-toolkit.md“PROBE docs-md: HTTP 404 at https://developer.nvidia.com/cuda-toolkit.md”
• [probe] https://developer.nvidia.com/openapi.json“PROBE openapi: all candidate paths 404 (https://developer.nvidia.com/openapi.json, https://developer.nvidia.com/swagger.json, https://developer.nvidia.com/api/openapi.json, https://developer.nvidia.com/.well-known/openapi.json)”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Plug MCP servers into this product so it can use their toolsweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Connect an agent via an official MCP serverweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Use an official CLIweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Drive the product through a documented public APIweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

• [claimed-docs] https://developer.nvidia.com/cuda-toolkit“The toolkit includes GPU-accelerated libraries, debugging and optimization tools, a C/C++ compiler, and a runtime library.”
• [probe] https://developer.nvidia.com/openapi.json“PROBE openapi: all candidate paths 404 (https://developer.nvidia.com/openapi.json, https://developer.nvidia.com/swagger.json, https://developer.nvidia.com/api/openapi.json, https://developer.nvidia.com/.well-known/openapi.json)”
• [probe] https://developer.nvidia.com/cuda-toolkit.md“PROBE docs-md: HTTP 404 at https://developer.nvidia.com/cuda-toolkit.md”

Issue scoped/least-privilege API credentials for an agentweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Build against official SDKsweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

• [claimed-docs] https://developer.nvidia.com/cuda-toolkit“The toolkit includes GPU-accelerated libraries, debugging and optimization tools, a C/C++ compiler, and a runtime library.”
• [claimed-docs] https://developer.nvidia.com/cuda-toolkit“cuTile Python is an expression of the CUDA Tile programming model in Python. It is built on top of the CUDA Tile IR specification and allows you to write tile kernels in Python.”
• [claimed-docs] https://developer.nvidia.com/rtx“The RTX Neural Shaders SDK lets developers train shader data on an RTX PRO workstation and accelerate neural representations with NVIDIA Tensor Cores at runtime.”
• [community] https://news.ycombinator.com/item?id=48508550“Those are SM120 so no tmem/tcgen05 and lack of support in main libraries... For that money I'd buy a single B300, similar total AI TOPS, similar GPU bandwidth aggregated, and only 25% less total memory, half the energy consumption”

Subscribe to events via webhooksweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Explore an interactive API reference with runnable examplesweight 2

n/a — not applicable to this product: excluded from numerator and denominator

• [probe] https://developer.nvidia.com/openapi.json“PROBE openapi: all candidate paths 404 (https://developer.nvidia.com/openapi.json, https://developer.nvidia.com/swagger.json, https://developer.nvidia.com/api/openapi.json, https://developer.nvidia.com/.well-known/openapi.json)”

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

n/a — not applicable to this product: excluded from numerator and denominator

• [probe] https://developer.nvidia.com/openapi.json“PROBE openapi: all candidate paths 404 (https://developer.nvidia.com/openapi.json, https://developer.nvidia.com/swagger.json, https://developer.nvidia.com/api/openapi.json, https://developer.nvidia.com/.well-known/openapi.json)”
• [probe] https://developer.nvidia.com/cuda-toolkit.md“PROBE docs-md: HTTP 404 at https://developer.nvidia.com/cuda-toolkit.md”

Test against a sandbox environment without touching production dataweight 1

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Rely on versioned APIs with a documented deprecation policyweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Do everything through the API that I can do in the UIweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Export all of my data in open formats and leaveweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Read the product's source under an open licenseweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Self-host the core productweight 3

3 (weight) × 7 (quality) × 1.0 (full) = 21.0 of 30 max

• [claimed-docs] https://www.nvidia.com/en-us/products/workstations/professional-desktop-gpus/rtx-pro-6000/“With 96 GB of memory on the RTX PRO 6000, you can turn your desktop into an AI powerhouse for fine-tuning LLMs, generative AI, and running autonomous AI agents locally and securely.”
• [claimed-docs] https://www.nvidia.com/en-us/products/workstations/professional-desktop-gpus/rtx-pro-6000/“the NVIDIA RTX PRO 6000 accelerates data science workflows—from exploration and model evaluation to visualization—without relying on costly cloud or data center resources.”
• [community] https://news.ycombinator.com/item?id=48508550“Converting four RTX PRO 6000 Blackwell cards to waterblocks, finding a VRM choke loose on the workbench, and getting back to 41k tok/s.”
• [community] https://news.ycombinator.com/item?id=48508550“Ok, how are people powering these things? 2.4kW is well beyond a standard circuit in the US. Are people having 240V/30A circuits installed?”

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Set up automations that run autonomously in the backgroundweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Operate the product with natural-language commandsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Perform bulk operations across many items at onceweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Define rules that trigger actions automatically on eventsweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh