AIbase
EN
Home
AI Models Finder
Sonar Pro
S

Sonar Pro

New version of Sonar search model. The model is further trained by Llama 3.3 70B, optimizes the search application and runs on the Cerebras inference infrastructure. Perplexity says that the new version of Sonar's Token decoding speed reaches 1,200 per second, which is more than 8.5 times that of Gemini 2.0 Flash, "can generate answers almost instantly."
Intelligence(Medium)
Speed(Relatively Fast)
Input Supported Modalities
Yes
Is Reasoning Model
200,000
Context Window
0
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

- /M tokens
Input
- /M tokens
Output
￥43.2 /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Sonar Pro
R1 1776
Sonar Reasoning

Basic Parameters

Sonar ProTechnical Parameters
Parameter Count
Not Announced
Context Length
200.00k tokens
Training Data Cutoff
Open Source Category
Proprietary
Multimodal Support
Text Only
Throughput
0
Release Date
2025-01-21
Response Speed
154.79,689 tokens/s

Benchmark Scores

Below is the performance of Sonar Pro in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
42.73
Large Language Model Intelligence Level
Coding Index
25.04
Indicator of AI model performance on coding tasks
Math Index
51.73
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
75.5
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
57.8
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
7.9
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
27.5
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
22.6
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
84.8
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
74.5
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
29
An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase