The AI arena is free today

Open Superagent

Mistral Small 3.2 24B Instruct vs Pixtral Large

Mistral Small 3.2 24B Instruct and Pixtral Large are closely matched at 8.4 and 11.8 on the LLM Stats Score. Mistral Small 3.2 24B Instruct is 28.2x cheaper per token.

Mistral AI · Mistral AI · Updated for 2026

Which is better?

Mistral Small 3.2 24B Instruct and Pixtral Large are closely matched on the overall LLM Stats Score at 8.4 and 11.8.

In the 5 individual benchmarks reported for both models, Pixtral Large wins 4; this is a narrower head-to-head signal than the composite indexes.

On price, Mistral Small 3.2 24B Instruct is roughly 28.2x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Mistral Small 3.2 24B Instruct

  • cost matters — it's about 28.2x cheaper per token
  • you want the most recent training data — it shipped Jun 2025

Choose Pixtral Large

  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 4 of 5 exact shared results

At a glance

The differences that matter most.

Mistral Small 3.2 24B Instruct
Mistral AI
Pixtral Large
Mistral AI
Core performance indexes
LLM Stats Score
8.4
#294
11.8
#272
Reasoning
7.9
#295
13.1
#256
Cost, coverage & limits
Benchmark wins
1 of 5
4 of 5
Input price
$0.07 / M
$2.00 / M
Output price
$0.20 / M
$6.00 / M
Context window
128,000
128,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Mistral Small 3.2 24B Instruct
Pixtral Large
Vision
10.1#134
10.9#126
Multimodal
13.1#114
13.2#113
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

15 reported for Mistral Small 3.2 24B Instruct · 7 for Pixtral Large

5 shared

Mistral Small 3.2 24B Instruct outperforms in 1 benchmarks (DocVQA), while Pixtral Large is better at 4 benchmarks (AI2D, ChartQA, MathVista, MMMU).

Pixtral Large significantly outperforms across most benchmarks.

Tue Oct 13 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Mistral Small 3.2 24B Instruct costs less

For input processing, Mistral Small 3.2 24B Instruct ($0.07/1M tokens) is 26.7x cheaper than Pixtral Large ($2.00/1M tokens).

For output processing, Mistral Small 3.2 24B Instruct ($0.20/1M tokens) is 30.0x cheaper than Pixtral Large ($6.00/1M tokens).

In conclusion, Pixtral Large is more expensive than Mistral Small 3.2 24B Instruct.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Tue Oct 13 2026 • llm-stats.com
Mistral AI
Mistral Small 3.2 24B Instruct
Input tokens$0.07
Output tokens$0.20
Best providerDeepinfra
Mistral AI
Pixtral Large
Input tokens$2.00
Output tokens$6.00
Best providerMistral
Notice missing or incorrect data?

Model Size

Parameter count comparison

100.4B diff

Pixtral Large has 100.4B more parameters than Mistral Small 3.2 24B Instruct, making it 425.4% larger.

Mistral AI
Mistral Small 3.2 24B Instruct
23.6Bparameters
Mistral AI
Pixtral Large
124.0Bparameters
23.6B
Mistral Small 3.2 24B Instruct
124.0B
Pixtral Large

Context Window

Maximum input and output token capacity

Both models have the same input context window of 128,000 tokens. Both models can generate responses up to 128,000 tokens.

Mistral AI
Mistral Small 3.2 24B Instruct
Input128,000 tokens
Output128,000 tokens
Mistral AI
Pixtral Large
Input128,000 tokens
Output128,000 tokens
Tue Oct 13 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Mistral Small 3.2 24B Instruct and Pixtral Large support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Mistral Small 3.2 24B Instruct

Text
Images
Audio
Video

Pixtral Large

Text
Images
Audio
Video

License

Usage and distribution terms

Mistral Small 3.2 24B Instruct is licensed under Apache 2.0, while Pixtral Large uses Mistral Research License (MRL) for research; Mistral Commercial License for commercial use.

License differences may affect how you can use these models in commercial or open-source projects.

Mistral Small 3.2 24B Instruct

Apache 2.0

Open weights

Pixtral Large

Mistral Research License (MRL) for research; Mistral Commercial License for commercial use

Open weights

Release Timeline

When each model was launched

Mistral Small 3.2 24B Instruct was released on 2025-06-20, while Pixtral Large was released on 2024-11-18.

Mistral Small 3.2 24B Instruct is 7 months newer than Pixtral Large.

Mistral Small 3.2 24B Instruct

Jun 20, 2025

1.3 years ago

7mo newer
Pixtral Large

Nov 18, 2024

1.9 years ago

Knowledge Cutoff

When training data ends

Mistral Small 3.2 24B Instruct has a documented knowledge cutoff of 2023-10-01, while Pixtral Large's cutoff date is not specified.

We can confirm Mistral Small 3.2 24B Instruct's training data extends to 2023-10-01, but cannot make a direct comparison without Pixtral Large's cutoff date.

Mistral Small 3.2 24B Instruct

Oct 2023

Pixtral Large

—

Provider Availability

Mistral Small 3.2 24B Instruct is available from DeepInfra. Pixtral Large is available from Mistral AI.

Mistral Small 3.2 24B Instruct

deepinfra logo
Deepinfra
Input Price:Input: $0.07/1MOutput Price:Output: $0.20/1M

Pixtral Large

mistral logo
Mistral
Input Price:Input: $2.00/1MOutput Price:Output: $6.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Mistral Small 3.2 24B Instruct and Pixtral Large side-by-side, then vote on the output you prefer.

Mistral Small 3.2 24B Instruct
✓ Preferred
Pixtral Large
Open in Playground

FAQ

Common questions about Mistral Small 3.2 24B Instruct vs Pixtral Large.

Which is better, Mistral Small 3.2 24B Instruct or Pixtral Large?

Mistral Small 3.2 24B Instruct and Pixtral Large are closely matched on the LLM Stats Score at 8.4 and 11.8. Mistral Small 3.2 24B Instruct is made by Mistral AI and Pixtral Large is made by Mistral AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Mistral Small 3.2 24B Instruct compare to Pixtral Large in benchmarks?

Mistral Small 3.2 24B Instruct scores DocVQA: 94.9%, AI2D: 92.9%, HumanEval Plus: 92.9%, ChartQA: 87.4%, IF: 84.8%. Pixtral Large scores AI2D: 93.8%, DocVQA: 93.3%, ChartQA: 88.1%, VQAv2: 80.9%, MM-MT-Bench: 74.0%.

Is Mistral Small 3.2 24B Instruct cheaper than Pixtral Large?

Mistral Small 3.2 24B Instruct is 26.7x cheaper for input tokens. Mistral Small 3.2 24B Instruct costs $0.07/M input and $0.20/M output via deepinfra. Pixtral Large costs $2.00/M input and $6.00/M output via mistral.

What are the context window sizes for Mistral Small 3.2 24B Instruct and Pixtral Large?

Mistral Small 3.2 24B Instruct supports 128K tokens and Pixtral Large supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Mistral Small 3.2 24B Instruct and Pixtral Large?

Key differences include LLM Stats Score (8.4 vs 11.8), input pricing ($0.07 vs $2.00/M), licensing (Apache 2.0 vs Mistral Research License (MRL) for research; Mistral Commercial License for commercial use). See the full comparison above for benchmark-by-benchmark results.

Related comparisons