Sonar Pro: benchmark results

Perplexity's higher-tier search-grounded API model for deeper retrieval with citations; the Sonar line builds on Llama 3.3 70B (2025). Provider: Perplexity. Released 2025-02-01. Access: API.

Unified ELO 1528 ± 1, rank #553 of 1392 rated models, from 15 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MedBrowseComp 12126.12Accuracy (%)83.3
DeepResearch Bench - Citation Accuracy79.72Score (%)75
BenchmarkList ECI107.5Capability Index (ECI)45.9
AA Humanity's Last Exam6.55Accuracy (%)42.9
SnakeBench19TrueSkill Rating35.6
DeepResearch Bench - Effective Citations16.75Effective Citations33.3
MedBrowseComp 5018Accuracy (%)33.3
AA GPQA Diamond57.78Accuracy (%)32.4
Artificial Analysis Intelligence Index3.61Intelligence Index30.3
LM Market Cap LMC Score40LMC Score (0-100)27.3
DeepResearch Bench - Readability41.07Score (%)6.8
DeepResearch Bench36.19Score (%)4.5

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