# Pave vs Radford: which do AI models recommend for compensation benchmarkin, October 2026

HR AI Recommendation Index, October 2026 Edition, Compensation benchmarking data. Three of fourteen models named Pave first on the direct prompt; zero named Radford. Page: https://hr-ai-index.com/rewards/compensation-benchmarking-data/pave-vs-radford/

| | First-choice share | Rank | Negative rate | Labels | Models naming it |
|---|---|---|---|---|---|
| Pave | 19% | #1 of 13 | 4% | 27 | 12 of 14 |
| Radford | 5% | #7 of 13 | 50% | 28 | 12 of 14 |

## The direct prompt, model by model

- Gemini 3.5 Flash: pave first (first choices: Pave) (alternatives: Figures, Payscale, Ravio, RepVue, Salary.com CompAnalyst)
- GLM 4.7 FlashX: pave first (first choices: Pave, Payscale Ascent) (alternatives: Figures, Salary.com CompAnalyst)
- GPT-6 Luna: pave first (first choices: Pave) (alternatives: Mercer Total Remuneration Survey, Payscale, Radford)
- Claude Haiku 4.5: neither first, one named (first choices: Payscale) (alternatives: Comprehensive, Lattice, Pave, SalaryCube)
- GPT-5.4 mini: neither first, one named (first choices: Payscale) (alternatives: Mercer Total Remuneration Survey, Radford, WTW)
- Perplexity Sonar: neither first, one named (first choices: Ravio) (alternatives: CompUp, Pave, Payfactors, Payscale Ascent, Salary.com CompAnalyst)
- DeepSeek V4 Flash: neither first, one named (first choices: Payscale) (alternatives: Pave, Salary.com CompAnalyst)
- Qwen 3.7 Flash: neither first, one named (first choices: Lattice) (alternatives: Comprehensive, Deel HR, Pave, SalaryCube)
- Kimi K2: neither first, one named (first choices: Payscale, SalaryCube) (alternatives: Figures, Pave, Ravio, Salary.com CompAnalyst)
- Muse Glimmer 30B: neither first, one named (first choices: SalaryCube) (alternatives: Pave, Salary.com CompAnalyst)
- Grok 4.1 Fast: neither named (first choices: SalaryCube) (alternatives: Payscale, Salary.com CompAnalyst)
- Mistral Small: neither named (first choices: Ravio, SalaryCube) (alternatives: CompUp, Figures)
- Llama 4 Maverick: neither named
- MiniMax M2.5: neither named (first choices: SalaryCube) (alternatives: CompUp, Lattice, Salary.com CompAnalyst)

## What the models said about Pave

- "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

- ""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)

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. Comparisons are drawn for the top eight products in each category. Published under CC BY 4.0; the output is the models' output, and nothing here is a recommendation by the index.