Pave vs Radford
Three of fourteen models named Pave first on the direct prompt; zero named Radford. Pave was named by twelve of the fourteen models and Radford by twelve and Pave carries 27 labels and Radford 28, so the shares are not directly comparable.
Named in six categories this edition.
Radford
criticized challengerNamed in three 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 compensation benchmarking data page.
By framing
PaveFirst choices, of fourteen modelsRadfordAcross every category in the October 2026 Edition, Pave and Radford were named in the same answer forty-three times, of the 219 answers naming Pave and the 97 naming Radford. In those answers Radford took the first choice seven times and Pave seventeen.
Every model, every framing
| Model | DirectRA | ParaphraseRA | ComparativeRA | Budget-constrainedRA | Scale-constrainedRA | NegativeRA |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | | | ||||
| GPT-5.4 mini | RA | RA | ||||
| Gemini 3.5 Flash | | RA | RA | RA | ||
| Perplexity Sonar | | | RA | |||
| Grok 4.1 Fast | RA | | ||||
| Mistral Small | RA | RA | ||||
| DeepSeek V4 Flash | RA | RA | | | RA | |
| Llama 4 Maverick | | |||||
| Qwen 3.7 Flash | RA | RA | RA | | RA | |
| Kimi K2 | RA | RA | | | ||
| GLM 4.7 FlashX | | | ||||
| MiniMax M2.5 | | | RA | |||
| GPT-6 Luna | RA | |||||
| Muse Glimmer 30B | | RA |
PaveRA Radford first choice named as an alternative argued againstblank: not namedEach cell is one answer, Pave on the left and Radford on the right.The direct prompt
Pave first, Radford an alternative
3 of 14 modelsRadford was named in the answer but not as the choice, or not at all.Neither was the first choice, one was named
7 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
Pave5%#3 of 12What the models said about Pave
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. One of one in this category shown.
“Pave is the most practical choice for many early-stage companies because it is explicitly called out as a free benchmarking option” Perplexity Sonar · budget prompt · first choice
What the models said about Radford
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of six in this category shown.
“"Why you should avoid traditional providers (Mercer, Radford, Willis Towers Watson)"” Muse Glimmer 30B · negative prompt · hard negative
“incredibly robust but requires manual survey participation, a higher budget, and more administrative effort than modern API-based systems” Gemini 3.5 Flash · paraphrase prompt · soft negative
“$15K–$80K+/yr with mandatory survey participation. Overkill for most mid-market B2B unless you're in tech/life sciences specifically.” DeepSeek V4 Flash · direct prompt · soft negative
“This makes Radford a top pick for companies looking for reliable, free salary benchmarking data without a significant financial investment.” Mistral Small · budget prompt · first choice
“Radford or Mercer are the top choices due to their industry-specific data and reliability” Mistral Small · paraphrase prompt · first choice
“1. Radford (Aon) — *Best for B2B Tech/SaaS*” Kimi K2 · 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.