PRODUCT COMPARISON
Compare synthetic research tools
Compare product uses, methods, validation evidence, data sources, access and pricing. Start with Aaru and Simile, or choose two or three other products.
Product records: 6 September 2026. Method and evidence sources linked below.
| Compare products | SimileBehavioral simulation | Electric TwinSynthetic audiences |
|---|---|---|
| Product category | Audience simulation | Audience simulation |
| Product | Behavioral simulation | Synthetic audiences |
| Overview | Human-behavior simulations designed to explore reactions to changing products, prices and policies. | An audience workspace for asking new questions of models built around customer research. |
| Data grounding | Simile describes combining observed behavior with surveys, interviews and experiments. | Electric Twin describes using surveys, focus groups and customer interviews to construct audiences. |
| Access | Contact sales | Contact sales |
| Pricing | Discuss scope with provider | Discuss scope with provider |
| Research method | Simile describes accepting a natural-language prompt specifying the population, situation and valid actions, then returning an estimated distribution over the actions. The supplier says its models train on observed signals such as transactions and usage data alongside surveys, interviews and experiments that provide information about motives and changing behavior. Simile describes a separate confidence model that estimates likely simulation error, then presents a confidence classification alongside the predicted result. | Electric Twin documents asking questions of a modeled audience about motivations, trade-offs and potential changes of mind, then drilling into the responses with follow-up questions. The provider lists concept and proposition testing, messaging and creative testing, pricing exploration, strategic decision support and audience deep-dives as common uses. |
| Validation evidence | Provider-reported confidence-model evaluation: Simile reports evaluating a question-level confidence model on roughly 8,600 held-out questions with five-fold cross-validation. It describes Total Variation Distance as the error measure for simulated versus observed distributions, and reports metrics for several confidence-model approaches. This is a provider-published technical evaluation of its confidence signal, not a universal estimate of simulation accuracy. Simile explicitly says a model may be accurate on average while being inaccurate for an individual case. | Reported hold-out performance: Electric Twin reports 95.5% on 1-MAE and 92% on its NDAM measure in its published methodology. Its site attributes independent validation to Professor Michael Muthukrishna at LSE and describes more than 50,000 evaluations. These figures and the claimed external validation are reported by the supplier. The described evaluation compares response distributions in a held-out test; it is not, on its own, evidence for every target audience or decision context. |
| Documented scope | Simile says its confidence score estimates possible error for one question. Its example says the actual error cannot be known until there is a real result to compare with. The supplier notes that questions about new prices, products, policies or other conditions concern outcomes that may not have happened before. Its published framework treats the mechanism behind behavior and the scope of available evidence as material to interpretation. | Electric Twin notes that 1-MAE can become more forgiving as answer options increase, which is why it also reports a normalized distribution measure. The two metrics should not be treated as interchangeable. The supplier says the first step is assessing the data available for a particular audience and communicating where that resulting model is reliable and where its limits are. |
| Method and evidence sources | ||
| Primary source | Provider documentation | Provider documentation |
Product comparisons
- Aaru vs Simile
Both describe population simulations. Aaru frames scenarios around a decision and stated conditions; Simile documents a question-level confidence model alongside its simulated action distributions.
- Fairgen Boost vs Toluna HarmonAIze Boost
Both work with a survey that has already been collected. Fairgen describes augmenting survey segments while preserving questionnaire structure; Toluna defines Boost as amplifying patterns after fieldwork.
- Qualtrics Synthetic Panels vs Synthetic Users
Qualtrics generates synthetic responses within its survey distribution workflow. Synthetic Users organizes audience-defined personas, projects and studies, with interviews, surveys and developer API access.
- Fairgen Twins vs Ipsos PersonaBot
Fairgen Twins supports structured studies and follow-up conversations with modeled respondents. Ipsos PersonaBot offers conversational access to personas from an existing segmentation study.