Zero of fourteen models named Greenhouse first on the direct prompt; zero named Prelude. Greenhouse was named by thirteen of the fourteen models and Prelude by nine and Greenhouse carries 23 labels and Prelude 14, so the shares are not directly comparable.
Named in fourteen 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 interview scheduling page.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | PR | |||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | PR | PR | ||||
| Perplexity Sonar | ||||||
| Grok 4.20 | PR | |||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | PR | |||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | PR | |||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 | ||||||
| GPT-6 Luna | PR | |||||
| Muse Glimmer 30B | PR | PR |
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.
No label in this category carried a quote.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“Legacy Tools (e.g., Prelude): ... Calendly has wound down this dedicated TA scheduling product.” Gemini 3.5 Flash · direct prompt · hard negative
“Prelude is being wound down by Calendly and should likely be avoided for new implementations” DeepSeek V4 Flash · comparative prompt · hard negative
“it's being wound down and shouldn't be on your shortlist” Kimi K2 · paraphrase prompt · hard negative
“The top tools for mid-market recruiting teams are typically ModernLoop, Prelude, or Grayscale” Muse Glimmer 30B · scale prompt · first choice
“look at recruiting-native schedulers like ModernLoop, Prelude, Grayscale, or candidate.fyi” GLM 4.7 FlashX · paraphrase prompt · alternative
“Prelude (Interview Schedule) (Runner-Up for Candidate Experience and Simplicity)” Grok 4.20 · direct 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.