Zero of fourteen models named Atlassian Compass first on the direct prompt; one named OpsLevel. Both were named by all fourteen models and Atlassian Compass carries 30 labels and OpsLevel 42, 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 internal developer portals page.
Across every category in the November 2026 Edition, Atlassian Compass and OpsLevel were named in the same answer fifty-six times, of the 97 answers naming Atlassian Compass and the 124 naming OpsLevel. In those answers OpsLevel took the first choice two times and Atlassian Compass two.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | ||||||
| Grok 4.20 | ||||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | ||||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | ||||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 | ||||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B |
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. Six of eight in this category shown.
“I would not start a new evaluation with Atlassian Compass as a standalone option.” GPT-6 Luna · scale prompt · hard negative
“Avoid for new implementations — Atlassian is winding this down” Kimi K2 · negative prompt · hard negative
“Ecosystem-centric portals like Atlassian Compass... can lack the deep extensibility or custom integration freedom” Gemini 3.5 Flash · negative prompt · soft negative
“The best internal developer portal for a company with a limited budget is Atlassian Compass, which is a cheap per-user IDP at $8/user/mo” Llama 4 Maverick · budget prompt · first choice
“Atlassian Compass is usually the best paid choice” Perplexity Sonar · budget prompt · first choice
“If you're already using Atlassian tools, Compass is the most budget-friendly paid option.” Mistral Small · budget prompt · alternative
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of seven in this category shown.
“Proprietary Closed‑Source Portals (e.g., Port.io, OpsLevel, Atlassian Compass) | *Vendor lock‑in.*” GLM 4.7 FlashX · negative prompt · soft negative
“proprietary portals (Port.io, OpsLevel, Atlassian Compass, etc.) carry vendor lock-in risks” Mistral Small · negative prompt · soft negative
“Proprietary SaaS IDPs with Rigid Lock-In (Port, Cortex, OpsLevel)... Data Model Lock-In” Gemini 3.5 Flash · negative prompt · soft negative
“I'd recommend Cortex or OpsLevel” MiniMax M2.5 · direct prompt · first choice
“OpsLevel if automated cataloging, service ownership, and enforcing engineering standards are the main goals.” GPT-6 Luna · direct prompt · alternative
“When to choose OpsLevel: If automated catalog discovery and "maturity" tracking are your biggest pain points” Grok 4.20 · paraphrase prompt · alternative
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.