How AMD Instinct MI355X’s scores are calculated

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

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

• [probe] https://rocm.docs.amd.com/llms.txt“PROBE llms.txt: HTTP 200 at https://rocm.docs.amd.com/llms.txt # ROCm documentation > Note: ROCm documentation is split across multiple projects. In addition to this file, each proje”
• [probe] https://rocm.docs.amd.com/en/latest/“PROBE runtime (recorded 2026-09-15): the ROCm documentation at rocm.docs.amd.com answered a keyless curl naming ROCm — the MI355X's entire developer toolchain surface is live and crawlable, unlike www.amd.com product pages, which reset connections for non-browser user agents (recorded at crawl).”
• [probe] https://rocm.docs.amd.com/en/latest/.md“PROBE docs-md: HTTP 404 at https://rocm.docs.amd.com/en/latest/.md”
• [probe] https://rocm.docs.amd.com/openapi.json“PROBE openapi: all candidate paths 404 (https://rocm.docs.amd.com/openapi.json, https://rocm.docs.amd.com/swagger.json, https://rocm.docs.amd.com/api/openapi.json, https://rocm.docs.amd.com/.well-known/openapi.json)”

Run the product headlessly / in CI for automationweight 2

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

• [claimed-docs] https://instinct.docs.amd.com/“GPU Operator Deploy and manage Instinct GPUs in Kubernetes clusters.”
• [claimed-docs] https://instinct.docs.amd.com/“Spur AI-native job scheduler, drop-in compatible with Slurm, with GPU-first scheduling and Raft-based state.”
• [claimed-docs] https://instinct.docs.amd.com/“Cluster Validation Suite Test scripts that validate AMD AI clusters end to end.”
• [claimed-docs] https://instinct.docs.amd.com/“AMD Container Toolkit Integrate Instinct GPUs with Docker and container runtimes.”
• [claimed-docs] https://instinct.docs.amd.com/“ROCm Validation Suite System validation and hardware diagnostics.”

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) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

• [claimed-docs] https://instinct.docs.amd.com/“AMD SMI Unified user-space tool to manage and monitor GPUs and drivers.”
• [claimed-docs] https://instinct.docs.amd.com/“Spur AI-native job scheduler, drop-in compatible with Slurm, with GPU-first scheduling and Raft-based state.”
• [claimed-docs] https://instinct.docs.amd.com/“AMD Container Toolkit Integrate Instinct GPUs with Docker and container runtimes.”

Drive the product through a documented public APIweight 3

3 (weight) × 4 (quality) × 0.6 (partial) = 7.2 of 30 max

• [claimed-docs] https://instinct.docs.amd.com/“HIP C++ Learn the HIP programming model.”
• [claimed-docs] https://instinct.docs.amd.com/“AMD SMI Unified user-space tool to manage and monitor GPUs and drivers.”
• [claimed-docs] https://instinct.docs.amd.com/“Device Metrics Exporter Prometheus-format GPU metrics for HPC and AI environments.”
• [probe] https://rocm.docs.amd.com/llms.txt“PROBE llms.txt: HTTP 200 at https://rocm.docs.amd.com/llms.txt # ROCm documentation > Note: ROCm documentation is split across multiple projects. In addition to this file, each proje”
• [probe] https://rocm.docs.amd.com/openapi.json“PROBE openapi: all candidate paths 404 (https://rocm.docs.amd.com/openapi.json, https://rocm.docs.amd.com/swagger.json, https://rocm.docs.amd.com/api/openapi.json, https://rocm.docs.amd.com/.well-known/openapi.json)”

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) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

• [claimed-docs] https://rocm.docs.amd.com/en/latest/“The foundational libraries, runtimes, and tools for GPU computing on AMD hardware — math and compute libraries, communication primitives, HIP runtime, profiling and debugging tools, and more.”
• [claimed-docs] https://rocm.docs.amd.com/en/latest/“Full-stack documentation and recipes to deploy AI workloads on AMD GPUs using popular ROCm-enabled frameworks.”
• [claimed-docs] https://rocm.docs.amd.com/en/latest/“Inference * [vLLM](https://rocm.docs.amd.com/projects/ai-ecosystem/en/latest/inference/vllm.html) * [SGLang](https://rocm.docs.amd.com/projects/ai-ecosystem/en/latest/inference/sglang.html)”
• [claimed-docs] https://instinct.docs.amd.com/“HIP C++ Learn the HIP programming model.”
• [claimed-docs] https://instinct.docs.amd.com/“OpenMP Explore the OpenMP programming model.”
• [claimed-docs] https://instinct.docs.amd.com/“AMD Container Toolkit Integrate Instinct GPUs with Docker and container runtimes.”
• [probe] https://rocm.docs.amd.com/llms.txt“PROBE llms.txt: HTTP 200 at https://rocm.docs.amd.com/llms.txt # ROCm documentation > Note: ROCm documentation is split across multiple projects. In addition to this file, each proje”
• [probe] https://rocm.docs.amd.com/en/latest/“PROBE runtime (recorded 2026-09-15): the ROCm documentation at rocm.docs.amd.com answered a keyless curl naming ROCm — the MI355X's entire developer toolchain surface is live and crawlable, unlike www.amd.com product pages, which reset connections for non-browser user agents (recorded at crawl).”

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

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

• [probe] https://rocm.docs.amd.com/openapi.json“PROBE openapi: all candidate paths 404 (https://rocm.docs.amd.com/openapi.json, https://rocm.docs.amd.com/swagger.json, https://rocm.docs.amd.com/api/openapi.json, https://rocm.docs.amd.com/.well-known/openapi.json)”
• [probe] https://rocm.docs.amd.com/en/latest/.md“PROBE docs-md: HTTP 404 at https://rocm.docs.amd.com/en/latest/.md”

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

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

• [probe] https://rocm.docs.amd.com/openapi.json“PROBE openapi: all candidate paths 404 (https://rocm.docs.amd.com/openapi.json, https://rocm.docs.amd.com/swagger.json, https://rocm.docs.amd.com/api/openapi.json, https://rocm.docs.amd.com/.well-known/openapi.json)”
• [probe] https://rocm.docs.amd.com/en/latest/.md“PROBE docs-md: HTTP 404 at https://rocm.docs.amd.com/en/latest/.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

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

• [claimed-docs] https://rocm.docs.amd.com/en/latest/“The foundational libraries, runtimes, and tools for GPU computing on AMD hardware — math and compute libraries, communication primitives, HIP runtime, profiling and debugging tools, and more.”
• [probe] https://rocm.docs.amd.com/openapi.json“PROBE openapi: all candidate paths 404 (https://rocm.docs.amd.com/openapi.json, https://rocm.docs.amd.com/swagger.json, https://rocm.docs.amd.com/api/openapi.json, https://rocm.docs.amd.com/.well-known/openapi.json)”
• [probe] https://rocm.docs.amd.com/llms.txt“PROBE llms.txt: HTTP 200 at https://rocm.docs.amd.com/llms.txt # ROCm documentation > Note: ROCm documentation is split across multiple projects. In addition to this file, each proje”

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) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

• [claimed-docs] https://instinct.docs.amd.com/“GPU Operator Deploy and manage Instinct GPUs in Kubernetes clusters.”
• [claimed-docs] https://instinct.docs.amd.com/“AMD Container Toolkit Integrate Instinct GPUs with Docker and container runtimes.”
• [claimed-docs] https://instinct.docs.amd.com/“Cluster Validation Suite Test scripts that validate AMD AI clusters end to end.”
• [claimed-docs] https://instinct.docs.amd.com/“Device Metrics Exporter Prometheus-format GPU metrics for HPC and AI environments.”
• [claimed-docs] https://instinct.docs.amd.com/“Spur AI-native job scheduler, drop-in compatible with Slurm, with GPU-first scheduling and Raft-based state.”
• [community] https://news.ycombinator.com/item?id=49141073“On every row the B300 beat the MI355X in a wafer.ai comparison; critics say the price comparison (MI355X at $2.5/hr) is unrealistic since no one is easily getting MI355X at that rate, and the B200 test unfairly spans two nodes with a cross-node all-reduce penalty.”

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) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

• [claimed-docs] https://rocm.docs.amd.com/en/latest/“Inference * [vLLM](https://rocm.docs.amd.com/projects/ai-ecosystem/en/latest/inference/vllm.html) * [SGLang](https://rocm.docs.amd.com/projects/ai-ecosystem/en/latest/inference/sglang.html)”
• [claimed-docs] https://rocm.docs.amd.com/en/latest/“Full-stack documentation and recipes to deploy AI workloads on AMD GPUs using popular ROCm-enabled frameworks.”
• [claimed-docs] https://instinct.docs.amd.com/“GPU Partitioning Split compute units and memory to partition a single GPU.”

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) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

• [claimed-docs] https://instinct.docs.amd.com/“Spur AI-native job scheduler, drop-in compatible with Slurm, with GPU-first scheduling and Raft-based state.”

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