Ashby vs Paradox
Six of fourteen models named Ashby first on the direct prompt; zero named Paradox. Ashby was named by twelve of the fourteen models and Paradox by thirteen and Ashby carries 28 labels and Paradox 21, so the shares are not directly comparable.
Named in seven categories this edition.
Named in eight 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 AI recruiting assistants page.
By framing
AshbyFirst choices, of fourteen modelsParadox
Across every category in the November 2026 Edition, Ashby and Paradox were named in the same answer forty-nine times, of the 244 answers naming Ashby and the 221 naming Paradox. In those answers Paradox took the first choice two times and Ashby four.
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 4.20 | | | | |||
| 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 | | | | |
Ashby Paradox first choice named as an alternative argued againstblank: not namedEach cell is one answer, Ashby on the left and Paradox on the right.The direct prompt
Ashby first, Paradox an alternative
6 of 14 modelsParadox was named in the answer but not as the choice, or not at all.Neither was the first choice, one was named
4 of 14 modelsThe answer put something else first and named one of the two as an alternative.Neither was named
4 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
Paradox8%#3 of 13Ashby0%#– of 13What the models said about Ashby
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Two of two in this category shown.
“including Greenhouse, Lever, and Ashby, may be in violation of the Fair Credit Reporting Act (FCRA)” Qwen 3.7 Flash · negative prompt · soft negative
“Ashby (potential FCRA issues in consumer reporting)” Grok 4.20 · negative prompt · soft negative
What the models said about Paradox
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Two of two in this category shown.
“Paradox's Olivia leads conversational screening and scheduling for high-volume hiring” Muse Glimmer 30B · comparative prompt · first choice
“Best Overall for Automated Screening & Scheduling: Paradox (Olivia)” 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.