AIbase
EN
Home
AI Models Finder
Aya Expanse 32B
A

Aya Expanse 32B

Large-scale language model focused on multilingual capabilities with 32B parameters providing powerful cross-language understanding and generation. Aya series renowned for excellent multilingual task performance, particularly excelling in low-resource languages and cross-language tasks. Suitable for international applications, multilingual customer service, cross-language content creation, and global enterprises requiring broad language support.
Intelligence(Weak)
Speed(Medium)
Input Supported Modalities
Yes
Is Reasoning Model
128,000
Context Window
-
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

- /M tokens
Input
- /M tokens
Output
￥5.4 /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Command A
Command-R+ (Apr '24)
￥0.25
Command-R+ (Aug '24)
￥0.25

Basic Parameters

Aya Expanse 32BTechnical Parameters
Parameter Count
Not Announced
Context Length
128.00k tokens
Training Data Cutoff
Open Source Category
Open Weights (License Required for Commercial Use)
Multimodal Support
Text Only
Throughput
Release Date
2024-10-24
Response Speed
118.03,091 tokens/s

Benchmark Scores

Below is the performance of Aya Expanse 32B in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
20.05
Large Language Model Intelligence Level
Coding Index
14.29
Indicator of AI model performance on coding tasks
Math Index
22.43
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
37.7
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
23
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
4.5
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
13.7
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
14.9
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
68.3
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
44.9
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
-
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