Zero of fourteen models named Amazon ECR first on the direct prompt; two named GitHub Packages. Amazon ECR was named by ten of the fourteen models and GitHub Packages by fourteen and Amazon ECR carries 14 labels and GitHub Packages 64, so the shares are not directly comparable.
Named in one category this edition.
Named in one category this edition.
Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all fourteen models, for a mid-market B2B company; rank is within the category; every quote names the model and the prompt it came from. Both figures come from the artifact and container registries page.
| Model | DirectAEGP | ParaphraseAEGP | ComparativeAEGP | Budget-constrainedAEGP | Scale-constrainedAEGP | NegativeAEGP |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | GP | GP | GP | |||
| GPT-5.4 mini | GP | AE | ||||
| Gemini 3.5 Flash | GP | GP | GP | GP | ||
| Perplexity Sonar | GP | AEGP | AEGP | GP | ||
| Grok 4.20 | GP | GP | GP | GP | ||
| Mistral Small | GP | AEGP | ||||
| DeepSeek V4 Flash | GP | AEGP | GP | GP | GP | GP |
| Llama 4 Maverick | GP | GP | GP | |||
| Qwen 3.7 Flash | AEGP | AE | GP | GP | ||
| Kimi K2 | GP | GP | GP | GP | GP | |
| GLM 4.7 FlashX | GP | GP | ||||
| MiniMax M2.5 | GP | AE | GP | GP | ||
| GPT-6 Luna | AEGP | AEGP | GP | |||
| Muse Glimmer 30B | AE | GP | GP |
Bold names in an answer are the products the judge labeled a first choice; a model naming several gives each of them that label. The full answer text for every row is in the record.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Four of five in this category shown.
“you should still: Ensure they are properly configured and not publicly exposed unless necessary.” Mistral Small · negative prompt · soft negative
“AWS workloads: Amazon ECR. It supports image scanning, lifecycle cleanup, and cross-account or cross-region replication.” GPT-6 Luna · paraphrase prompt · first choice
“Primarily AWS, ECS/EKS/Fargate today → start with Amazon ECR for zero egress pull costs inside AWS and IAM-native access.” Muse Glimmer 30B · paraphrase prompt · first choice
“Best default for most mid-sized B2B companies: AWS ECR, ACR, or Artifact Registry depending on your cloud.” GPT-5.4 mini · paraphrase prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“public registries like Docker Hub, GitHub Container Registry (GHCR), or Google Artifact Registry are convenient, they pose high risks” Qwen 3.7 Flash · negative prompt · hard negative
“only if you're very GitHub-centric and your package format needs are modest, since it is narrower in scope” GPT-5.4 mini · direct prompt · soft negative
“you should still: Ensure they are properly configured and not publicly exposed unless necessary.” Mistral Small · negative prompt · soft negative
“start with GitHub Packages (free with your plan) and migrate to JFrog Artifactory once you outgrow it” DeepSeek V4 Flash · direct prompt · first choice
“Top Recommendation: Azure Container Registry (ACR) or GitHub Container Registry (GHCR)” Kimi K2 · paraphrase prompt · first choice
“Start with GitHub Packages / GitLab if your stack is standard.” Gemini 3.5 Flash · direct prompt · first choice
Comparisons are drawn for the top eight products in each category, each against each. The output is the models' output; nothing here is a recommendation by the index.