Sonar: benchmark results

Perplexity's search-grounded API model built on Llama 3.3 70B and served on Cerebras hardware for fast, cited real-time answers (February 2025). Provider: Perplexity. Released 2025-02-11. Access: API.

Unified ELO 1544 ± 1, rank #465 of 1392 rated models, from 14 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AI for Education Pedagogy - Technology77.36Accuracy (%)44.5
Gapminder AI Worldview78.4Correct Rate (%)44.1
AI for Education Pedagogy - Social studies71.82Accuracy (%)37.4
AI for Education Pedagogy - Primary76.53Accuracy (%)33.2
BenchmarkList ECI99.51Capability Index (ECI)32.9
Artificial Analysis Intelligence Index3.84Intelligence Index30.9
AA Humanity's Last Exam4.88Accuracy (%)28.5
AI for Education Pedagogy70.75Accuracy (%)28.2
AI for Education Pedagogy - Secondary69.34Accuracy (%)27.3
LM Market Cap LMC Score40LMC Score (0-100)27.3
AI for Education Pedagogy - Science66.67Accuracy (%)23.7
AI for Education Pedagogy - Maths64.29Accuracy (%)22.7

Interactive version: theaggregate.ai/model?slug=sonar · How It Works · Data refreshed daily, snapshot 2026-09-05.