Mixtral 8x22B Instruct

← AI Models
Mistral
2024-04-17
Modality:
Intelligence
9.8
#448/523
Coding
Math
Speed
Pricing
Google Preferred Source

Mixtral 8x22B Instruct is Mistral’s offering for advanced instruction-based tasks. It features an Intelligence Index of 9.8, targeting professional users who require high-quality instruction processing.

When to Use Mixtral 8x22B Instruct

✓ Best For

  • Instruction-based applications
  • Professional training tools
  • Complex query handling

✗ Not Ideal For

  • Real-time processing due to 0 tok/sec speed
  • Applications requiring immediate output due to 0s TTFT

How Mixtral 8x22B Instruct Compares

Intelligence Index · Higher is better

AlibabaMistralMeta

Benchmark Profile

Intelligence · Coding · Math

Intelligence Coding Math

All Benchmark Scores (7)

BenchmarkScore
Intelligence Index 9.8
MMLU-Pro 537%
GPQA 332%
LiveCodeBench 148%
HLE 41%
SciCode 18.8%
MATH 500 54.5%

Data: Artificial Analysis · Updated: April 10, 2026

Frequently Asked Questions (15)

When was Mixtral 8x22B Instruct released?
Mixtral 8x22B Instruct was released on April 17, 2024.
Who created Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct was created by Mistral.
How intelligent is Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct scores 10 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 13).
Is Mixtral 8x22B Instruct a reasoning model?
No, Mixtral 8x22B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Mixtral 8x22B Instruct support?
Mixtral 8x22B Instruct supports text only input.
What output modalities does Mixtral 8x22B Instruct support?
Mixtral 8x22B Instruct supports text only output.
Can Mixtral 8x22B Instruct process images?
No, Mixtral 8x22B Instruct does not support image input. It can only process text.
Is Mixtral 8x22B Instruct multimodal?
No, Mixtral 8x22B Instruct is not multimodal. It only supports text only input.
What is the context window of Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct has a context window of 65k tokens. This determines how much text and conversation history the model can process in a single request.
Is Mixtral 8x22B Instruct open source?
Yes, Mixtral 8x22B Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
How many parameters does Mixtral 8x22B Instruct have?
Mixtral 8x22B Instruct has 141 billion parameters (39 billion active).
What are the active parameters of Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct is a Mixture of Experts (MoE) model with 141 billion total parameters, but only 39 billion active parameters are used during inference.
What is the license for Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct is released under the Apache 2.0 license. This license allows commercial use.
How does Mixtral 8x22B Instruct perform on benchmarks?
Mixtral 8x22B Instruct achieves a score of 10 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Is Mixtral 8x22B Instruct available via API?
Mixtral 8x22B Instruct is an open weights model that can be self-hosted.