Perplexity AIproprietary
Released: 2024-11-15Sonar
Lightweight, ultra-low latency conversational search engine model designed for instant lookup and summarization.
Intelligence Index
81.0/ 100
Calibrated multi-domain compositeThroughput Speed
92tok/sec
Output streaming throughputTime To First Token
290ms
Initial chunk server latencyLiveBench Contam-Free
74.0%
September 2026 suite scoreLiveBench Multi-Domain Evaluation Breakdown
Monthly refreshed contamination-free test setsLogical Reasoning78.0%
Coding & Repo Repair73.0%
Mathematics (AIME)76.5%
Data Analysis & Tables71.5%
Language & Comprehension72.0%
Instruction Following73.0%
Sourced Benchmark Evaluations (3)
Verified performance across authoritative benchmarks with provenance tracking.OpenAI Compatible API ExecutionAPI Ready
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="sonar",
messages=[{"role": "user", "content": "Evaluate multi-step logic problem"}],
temperature=0.2
)
print(response.choices[0].message.content)Evaluation & Sourcing Notes
Scores listed for Sonar represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.