# Asked the same question twice, the models moved their own first choice 71% of the time. The leader still held in 23 of 30 readings (10 categories at three buyer sizes).

HR AI Recommendation Index, October 2026 Edition. Page: https://hr-ai-index.com/research/repeat-measurement/

Ten categories were asked again three days after the edition run, with nothing changed: the same prompts, the same model versions, the same settings, one buyer segment, six framings, fourteen models, 840 answers. Whatever differs between the two runs is noise, and the noise is what this page measures. That is the reason the index asks every question six ways of every model rather than once: on its own, one ask moved 71% of the time; eighty-four, read together, are what the index reports.

## Model by model

- GLM 4.7 FlashX: 92% of 40 pairs flipped
- Mistral Small: 89% of 38 pairs flipped
- Qwen 3.7 Flash: 86% of 43 pairs flipped
- MiniMax M2.5: 81% of 36 pairs flipped
- Kimi K2: 78% of 40 pairs flipped
- Claude Haiku 4.5: 74% of 34 pairs flipped
- DeepSeek V4 Flash: 71% of 42 pairs flipped
- Grok 4.1 Fast: 69% of 45 pairs flipped
- Llama 4 Maverick: 68% of 28 pairs flipped
- Muse Glimmer 30B: 67% of 42 pairs flipped
- GPT-5.4 mini: 66% of 35 pairs flipped
- Gemini 3.5 Flash: 61% of 44 pairs flipped
- GPT-6 Luna: 46% of 35 pairs flipped
- Perplexity Sonar: 39% of 38 pairs flipped

## Category by category

| Category | Leader | Share, run one | Share, repeat | Move | Leader |
|---|---|---|---|---|---|
| Contingent workforce man | VectorVMS | 26% | 8% | -18 points | changed: SimpleVMS |
| Coaching platforms | BetterUp | 46% | 31% | -15 points | held |
| Global payroll | Deel | 33% | 46% | 14 points | held |
| Performance management | Lattice | 43% | 56% | 13 points | held |
| Compensation benchmarkin | Mercer Total Remuneration Survey | 44% | 33% | -11 points | held |
| Performance management | Betterworks | 37% | 28% | -9 points | changed: Workday HCM Performance Management |
| Contingent workforce man | SAP Fieldglass | 42% | 34% | -8 points | held |
| AI recruiting assistants | Eightfold AI | 44% | 36% | -8 points | held |
| Global payroll | G-P | 23% | 15% | -7 points | changed: Deel |
| Employee engagement surv | Workleap Officevibe | 41% | 34% | -7 points | held |
| Compensation benchmarkin | Payscale | 19% | 26% | 7 points | held |
| AI recruiting assistants | Manatal | 31% | 24% | -7 points | held |
| Learning management syst | Docebo | 40% | 46% | 6 points | held |
| Employee engagement surv | Culture Amp | 37% | 31% | -6 points | held |
| Employee onboarding | BambooHR | 34% | 28% | -6 points | changed: Gusto |
| Global payroll | Deel | 30% | 35% | 6 points | held |
| Coaching platforms | Growthspace | 20% | 15% | -5 points | held |
| Learning management syst | TalentLMS | 75% | 71% | -4 points | held |
| Contingent workforce man | VectorVMS | 16% | 20% | 4 points | held |
| Employee onboarding | Workday | 47% | 50% | 3 points | held |
| Performance management | Zoho People | 18% | 15% | -3 points | changed: 15Five |
| Learning management syst | TalentLMS | 51% | 48% | -3 points | held |
| Employee engagement surv | Culture Amp | 29% | 32% | 3 points | held |
| AI recruiting assistants | Manatal | 29% | 32% | 3 points | held |
| Benefits administration | Gusto | 20% | 18% | -2 points | changed: Employee Navigator |
| Compensation benchmarkin | Pave | 30% | 32% | 2 points | held |
| Employee onboarding | Rippling | 25% | 26% | 1 point | changed: BambooHR |
| Benefits administration | Gusto | 62% | 61% | -1 points | held |
| Coaching platforms | 15Five | 11% | 10% | -1 points | held |
| Benefits administration | ADP Workforce Now | 30% | 30% | 1 point | held |

Share floor: 13 points (the 90th percentile); median move 6 points; largest 18 points. Pooled flip rate 71%.

Published under CC BY 4.0. The output is the models' output; nothing here is a recommendation by the index.