Elicit
65
/100 Laddoo
FADING
Public-surface review of Elicit
Proof depth—
Claim coverage—
Evidence count—
Momentum—
Updated2026-05-01
Elicit vs Perplexity
Independent side-by-side comparison from Hlido. Both agents tested with the same evidence-first methodology — claims verified, scores normalized to the Laddoo scale (0-100). Updated 2026-06-11.
Perplexity
53
/100 Laddoo
FADING
AI-powered answer engine with cited sources. Public no-login basic queries. Pro tier for advanced reasoning models.
Proof depth—
Claim coverage—
Evidence count—
Momentum—
Updated2026-05-01
Hlido verdict
Hlido tested both. Elicit scored 65 (FADING); Perplexity scored 53 (FADING). Elicit leads by 12 points. Scores reflect verified claims, evidence depth, momentum, and surface coverage at the time of the most recent test. Re-tested periodically — drift over time is itself a signal.
Editorial verdict — side by side
From each agent's Hlido editorial scorecard: what it does well and where it falls short, in the editor's own words.
Elicit
Elicit struggles to maintain relevance in the research tools space — lacks clear differentiation and user engagement.
Falls short:
- No verified claims or features presented on the public surface
- Lacks clear differentiation from competing research tools
- Insufficient user engagement or community feedback
Perplexity
The answer engine that ships sources by default — solid for fact-shaped questions, increasingly serious for agent retrieval, but the moat keeps narrowing as every other lab catches up.
Does well:
- Every answer ships with inline citations to live web sources
- Sonar API is real and agent-driveable for retrieval-augmented workflows
- Real-time freshness is consistently better than chat products without web search
Falls short:
- Differentiation versus ChatGPT Search and Claude-with-web is narrower than the brand suggests
- Pages (longform mode) feels orthogonal to the search-first core
- Comet browser is unproven and confusingly positioned alongside the main product