Zero of twelve models named ChatGPT first on the direct prompt; one named Rippling. ChatGPT was named by eight of the twelve models and Rippling by nine and ChatGPT carries 11 labels and Rippling 14, so the shares are not directly comparable.
Named in seven categories this edition.
Named in twenty-eight categories this edition.
Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all twelve 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 HR AI assistants 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 4.1 Fast | ||||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | ||||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | ||||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 |
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.
“OpenAI, ChatGPT, or similar consumer tools used by HR without proper governance - Why to avoid: Lack of confidentiality, privacy, accuracy, and accountability safeguards” GLM 4.7 FlashX · negative prompt · hard negative
“the best AI assistant for an HR team is usually ChatGPT or Claude for drafting and internal support tasks” Perplexity Sonar · budget prompt · first choice
“A general-purpose writing assistant (ChatGPT or Claude) — The cheapest and most flexible option.” DeepSeek V4 Flash · budget prompt · first choice
“My top pick for most limited budgets: Start with ChatGPT (free) for content creation” Kimi K2 · budget prompt · first choice
No label in this category carried a quote.
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.