Perplexity: Sonar Deep Research

Executes iterative web searches across multiple steps, autonomously deciding which sources to retrieve, read, and evaluate based on intermediate findings. The model refines its search strategy dynamically—reformulating queries, prioritizing high-relevance sources, and abandoning unproductive paths—without requiring explicit user guidance between steps. This is implemented via an internal planning loop that treats web search as a first-class reasoning primitive rather than a post-hoc lookup mechanism.

Aggregates information from multiple retrieved sources, identifies contradictions or conflicting claims, and synthesizes a coherent narrative that acknowledges uncertainty and divergent viewpoints. The model evaluates source credibility implicitly (based on domain authority signals, citation patterns, and consistency with other sources) and weights claims accordingly. This synthesis happens during generation, not as a post-processing step, allowing the model to reason about source reliability while composing its response.

Generates responses grounded in real-time web search results rather than relying solely on training data. The model retrieves current information from the web, integrates it into its reasoning context, and generates answers that reflect up-to-date facts, recent events, and current data. This is implemented via a search-augmented generation pipeline where web results are fetched, ranked, and injected into the model's context window before generation, ensuring factuality for time-sensitive queries.

Refines search and reasoning strategies based on intermediate results, automatically reformulating queries when initial searches yield insufficient or irrelevant results. The model evaluates whether retrieved information answers the original question, identifies gaps, and adjusts its approach—changing keywords, broadening/narrowing scope, or pivoting to related topics. This feedback loop is internal to the model's reasoning process, not exposed to the user, enabling adaptive exploration without explicit user intervention.

Generates responses with explicit citations to source URLs, enabling users to verify claims and trace reasoning back to original sources. Citations are embedded in the response text or provided as structured metadata, linking specific claims to the web sources that support them. This is implemented by maintaining a mapping between generated text and retrieved sources during generation, ensuring citations are accurate and traceable.

Generates comprehensive, multi-paragraph research summaries that synthesize information across dozens of sources into coherent narratives with clear structure (introduction, key findings, trade-offs, limitations). The model organizes information hierarchically, prioritizes important findings, and provides context for how different pieces of information relate. Output can be formatted as structured sections (e.g., JSON with 'summary', 'key_findings', 'limitations', 'sources') or as flowing prose with implicit organization.

Applies domain-specific reasoning patterns and expert knowledge to research queries, adapting its approach based on the topic domain (e.g., scientific research, legal analysis, financial modeling). The model implicitly recognizes domain context from the query and adjusts its search strategy, source evaluation, and synthesis approach accordingly. For example, scientific queries may prioritize peer-reviewed sources and methodology evaluation, while financial queries may emphasize recent data and regulatory context.

Explicitly signals confidence levels and uncertainty in its responses, distinguishing between well-supported claims (backed by multiple sources), speculative claims (based on limited evidence), and areas where expert disagreement exists. The model may use explicit language ('likely', 'uncertain', 'experts disagree') or structured confidence metadata to communicate epistemic status. This is implemented by evaluating source agreement, source credibility, and evidence strength during synthesis.

Systematically compares and contrasts different viewpoints, approaches, or solutions to a problem, organizing information to highlight similarities, differences, and trade-offs. The model searches for and synthesizes multiple perspectives (e.g., different schools of thought, competing products, alternative methodologies), explicitly comparing them on relevant dimensions. This is implemented by treating comparative analysis as a structured reasoning task where the model identifies comparison dimensions, retrieves information for each perspective, and synthesizes findings into a comparison matrix or narrative.

Supports multi-turn conversations where users can ask follow-up questions, request clarification, or ask the model to dive deeper into specific aspects of previous research. The model maintains context across turns, refining its search and synthesis based on conversational feedback. For example, a user might ask 'What are the latest developments in quantum computing?', then follow up with 'Tell me more about error correction approaches', and the model will search for and synthesize information specific to that subtopic while maintaining context from the initial query.