Pixtral 12B (2409)

Data to be translated: A multimodal model with 12 billion parameters. Its visual encoder contains 400 million parameters and can understand natural images and documents. While performing multimodal tasks, its text-only performance remains strong. It supports images of variable sizes and multiple images in the context.

Intelligence(Relatively Weak)

Speed(Relatively Slow)

Input Supported Modalities

Yes

Is Reasoning Model

128,000

Context Window

8,192

Maximum Output Tokens

Knowledge Cutoff

Go Compare

Pricing

￥1.08 /M tokens

Input

￥1.08 /M tokens

Output

￥1.08 /M tokens

Blended Price

Quick Simple Comparison

Input

Output

Devstral

￥0.1

Devstral Medium

￥0.4

Devstral Small (May '25)

￥0.1

Basic Parameters

Pixtral 12B (2409)Technical Parameters

Parameter Count

12,400.0M

Context Length

128.00k tokens

Training Data Cutoff

Open Source Category

Open Weights (Permissive License)

Multimodal Support

Text, Image

Throughput

Release Date

2024-09-11

Response Speed

99.74,224 tokens/s

Benchmark Scores

Below is the performance of Pixtral 12B (2409) in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.

Intelligence Index

Large Language Model Intelligence Level

23.36

Large Language Model Intelligence Level

Coding Index

Indicator of AI model performance on coding tasks

12.54

Indicator of AI model performance on coding tasks

Math Index

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

22.9

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

MMLU Pro

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

47.3

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

GPQA

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

34.3

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

HLE

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

5.3

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

LiveCodeBench

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

11.5

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

SciCode

The model's capability in code generation for scientific computing or specific scientific domains

13.5

The model's capability in code generation for scientific computing or specific scientific domains

HumanEval

Score achieved by the AI model on the specific HumanEval benchmark test set

77.7

Score achieved by the AI model on the specific HumanEval benchmark test set

Math 500 Score

Score on the first 500 larger, more well-known mathematical benchmark tests

45.8

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)

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

131k

Context Length

Gemini 2.0 Flash Lite (Preview)

Output tokens/million

Output tokens/million

33k

Context Length

Qwen2.5 Coder Instruct 32B

Output tokens/million

131k

Context Length

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご