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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MedBrowseComp 121 | 26.12 | Accuracy (%) | 83.3 |
| DeepResearch Bench - Citation Accuracy | 79.72 | Score (%) | 75 |
| BenchmarkList ECI | 107.5 | Capability Index (ECI) | 45.9 |
| AA Humanity's Last Exam | 6.55 | Accuracy (%) | 42.9 |
| SnakeBench | 19 | TrueSkill Rating | 35.6 |
| DeepResearch Bench - Effective Citations | 16.75 | Effective Citations | 33.3 |
| MedBrowseComp 50 | 18 | Accuracy (%) | 33.3 |
| AA GPQA Diamond | 57.78 | Accuracy (%) | 32.4 |
| Artificial Analysis Intelligence Index | 3.61 | Intelligence Index | 30.3 |
| LM Market Cap LMC Score | 40 | LMC Score (0-100) | 27.3 |
| DeepResearch Bench - Readability | 41.07 | Score (%) | 6.8 |
| DeepResearch Bench | 36.19 | Score (%) | 4.5 |
Interactive version: theaggregate.ai/model?slug=sonar-pro · How It Works · Data refreshed daily, snapshot 2026-09-05.