crawler-status-logs-v1
AI API Hunt
S

Sonar Reasoning

Last updated: Recently

Model Type

MText

Max Context

127K

Max Output

-

Parameter Scale

-

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. 127,072 token context window. Includes independent benchmarks from Artificial Analysis.

Input Modality

text, image

Output Modality

text

Inference Speed

-

Latest Release Date

1/28/2025

SDK Ecosystem

-

artificial-analysismanufactureraa-bootstrap
Model Overview Fields

name

Sonar Reasoning

Release date

1/28/2025

Performance

-

model_creator.name

Perplexity

AA Evaluation Scores

AA Intelligence Index

17.9

AA Coding Index

-

AA Math Index

-

MMLU Pro

-

GPQA

0.623

HLE

-

LiveCodeBench

-

SciCode

-

Math-500

0.921333333333333

AIME

0.77

AIME 2025

-

IFBench

-

LCR

-

TerminalBench Hard

-

TAU2

-

Output Speed (tokens/s)

-

TTFT (s)

-

First Answer Token (s)

-

Perplexity logo

Perplexity

Sonar Reasoning logo

Sonar Reasoning

$0.00/M$0.00/M

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. 127,072 token context window. Includes independent benchmarks from Artificial Analysis.

00
0.0
Share:
Report / Feedback