Mistral: Pixtral Large 2411

Mistral: Pixtral Large 2411

mistralai · Released Nov 19, 2024 Efficient
Intelligence #149 / 583
48.6 Our Score
Speed #193 / 276
61.3 tokens / sec
Input #488 / 583
$2.00 per 1M tokens
Output #474 / 583
$6.00 per 1M tokens
Context #240 / 583
131,072 tokens

Analysis Summary

Mistral Pixtral Large 2411 is Mistral AI's multimodal flagship from late 2024, combining vision with tool use and function calling. Its intelligence index of 8.1 and agentic index of 36.5 place it above Mistral Large 2407 on both dimensions, and its GPQA of 0.505 and MMLU-Pro of 0.701 reflect strong general knowledge. The text+image+file modality supports document and image analysis in a single model.

For businesses, it is well suited to multimodal content workflows, document processing, and tool-augmented pipelines where image understanding is needed. Its instruction-following score (ifbench 0.345) is reasonable for structured output tasks. The main limitation is that its intelligence index remains in the mid-tier relative to the current field.

At $2.00 input and $6.00 output per million tokens, pricing matches Mistral Large 2407 but delivers more capability breadth. Teams needing vision plus tool use from a single model at this price point will find Pixtral Large a practical choice.

Assessed June 17, 2026

Editorial notes

Mistral Pixtral Large 2411 adds vision to Mistral's flagship with a strong agentic index of 36.5, tool use, and function calling, making it a versatile option for multimodal business workflows.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence2.1Technical4.5Value6.8Content6
Intelligence 2.1/10
Technical 4.5/10
Content 6/10
Value 6.8/10

How Mistral: Pixtral Large 2411 compares

Mistral: Pixtral Large 2411 ranks #261 of 380 AI models we track for overall intelligence, #124 of 292 for agentic tasks. Its 131K-token context window is larger than 59% of the models we list. At $2.00 per million input tokens it is cheaper than 16% of comparable models.

About Mistral: Pixtral Large 2411

Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of Mistral Large 2. The model is able to understand documents, charts and natural images. The model is..

Capabilities

Tool Use Function Calling Vision

Performance Indices

Source: Artificial Analysis

8.1 Intelligence Index
36.5 Agentic Index
2.3 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 50.5% Graduate-level scientific reasoning
HLE 3.6% Humanity's Last Exam
MMLU Pro 70.1% Multi-task language understanding
MATH 500 71.4% Mathematical problem-solving
AIME 7% Competition mathematics
AIME 2025 2.3% Competition mathematics (2025)
SciCode 29.2% Scientific computing

Technical

LiveCodeBench 26.1% Live coding evaluation
τ²-Bench 36.5% Conversational agent benchmark

Content

IFBench 34.5% Instruction following
LCR 10.3% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does Mistral: Pixtral Large 2411 stack up?

Compare side-by-side with other efficient models.

Compare Models

Model Information

OpenRouter ID mistralai/pixtral-large-2411
Providermistralai
Release Date November 19, 2024
Context Length131,072 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $2.00 $0.002000
Output $6.00 $0.006000

Leaderboard Categories

Frequently asked questions about Mistral: Pixtral Large 2411

How much does Mistral: Pixtral Large 2411 cost?

Mistral: Pixtral Large 2411 costs $2.00 per million input tokens and $6.00 per million output tokens.

What is the context window of Mistral: Pixtral Large 2411?

Mistral: Pixtral Large 2411 has a context window of 131,072 tokens (131K).

What can Mistral: Pixtral Large 2411 do?

Mistral: Pixtral Large 2411 supports image/vision input, tool use, and function calling.

Who created Mistral: Pixtral Large 2411?

Mistral: Pixtral Large 2411 is developed by Mistral and was released on November 19, 2024.