Gem vs Phenom
Three of fourteen models named Gem first on the direct prompt; one named Phenom. Gem was named by eight of the fourteen models and Phenom by thirteen and Gem carries 12 labels and Phenom 30, so the shares are not directly comparable.
Named in seven categories this edition.
Named in six categories 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 recruitment marketing and career sites page.
By framing
GemFirst choices, of fourteen modelsPhenom
Across every category in the October 2026 Edition, Gem and Phenom were named in the same answer fifty-four times, of the 221 answers naming Gem and the 294 naming Phenom. In those answers Phenom took the first choice four times and Gem eleven.
Every model, every framing
| 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 | | |||||
| GPT-6 Luna | | |||||
| Muse Glimmer 30B | | |
Gem Phenom first choice named as an alternative argued againstblank: not namedEach cell is one answer, Gem on the left and Phenom on the right.The direct prompt
Gem first, Phenom not the choice
3 of 14 modelsPhenom was named in the answer but not as the choice, or not at all.Phenom first, Gem not the choice
1 of 14 modelsGem was named in the answer but not as the choice, or not at all.Neither was the first choice, one was named
1 of 14 modelsThe answer put something else first and named one of the two as an alternative.Neither was named
9 of 14 modelsThe answer made no first choice from these two in this category.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.
By buyer segment
Phenom35%#1 of 13Gem2%#– of 13What the models said about Gem
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Three of three in this category shown.
“they may not be beneficial if your recruitment pipelines are already cold or inactive” Mistral Small · negative prompt · soft negative
“Gem is the best overall due to its strong automation, CRM, and AI features, as well as its high user satisfaction and mid-market focus.” Mistral Small · direct prompt · first choice
“Look for modern, agile platforms (such as Gem, Clinch, or Teamtailor) where implementation takes weeks, not quarters.” Gemini 3.5 Flash · scale prompt · first choice
What the models said about Phenom
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Five of five in this category shown.
“the best approach is to avoid high-end, enterprise-only "Recruitment Marketing Platforms" (RMPs) like Phenom, Beamery, or Symphony Talent” Gemini 3.5 Flash · budget prompt · hard negative
“Be cautious of platforms like Beamery, Avature, or Phenom People. ... built for the Fortune 500” Gemini 3.5 Flash · direct prompt · hard negative
“Phenom is a massive, AI-powered "Talent Experience Management" (TXM) platform. It is best known for creating highly personalized, consumer-grade front-end career sites.” Gemini 3.5 Flash · comparative prompt · first choice
“I recommend Phenom or MokaHR for a mid-sized B2B company seeking a powerful, AI-driven career site builder” Mistral Small · paraphrase prompt · first choice
“1. Phenom or Symphony Talent - These are among the top-ranked branded careers site builders for 2026” Claude Haiku 4.5 · 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.