One of fourteen models named Skills Base first on the direct prompt; zero named Lightcast Open Skills. Skills Base was named by twelve of the fourteen models and Lightcast Open Skills by twelve and Skills Base carries 23 labels and Lightcast Open Skills 18, so the shares are not directly comparable.
Named in two categories 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 skills intelligence page.
| 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. Three of four in this category shown.
“the consensus pricing comparison points to Skills Base as the lowest-cost skills intelligence / skills-matrix option that still functions as a full platform” Muse Glimmer 30B · budget prompt · first choice
“For most budget-conscious companies, Skills Base offers the best balance of features, genuinely usable free tier, and low per-user cost.” DeepSeek V4 Flash · budget prompt · first choice
“Skills Base stands out as the best skills intelligence platform for companies with a limited budget.” Grok 4.20 · budget prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Five of six in this category shown.
“Avoid These if Budget is a Constraint ... Lightcast ... priced via quote only and typically target enterprises” DeepSeek V4 Flash · budget prompt · hard negative
“Avoid for mid-market: ... or Lightcast—they're often overkill” Grok 4.20 · direct prompt · hard negative
“my default for a mid-sized B2B company would be Lightcast as the external reference taxonomy, with a small company-specific layer” GPT-6 Luna · paraphrase prompt · first choice
“Skills taxonomy: Lightcast Open Skills as the reference taxonomy, customized to your roles and terminology.” Perplexity Sonar · paraphrase prompt · first choice
“Best Overall for Data & API-First Integration: Lightcast (Skills API & Open Taxonomy)” Gemini 3.5 Flash · paraphrase 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.