The AI arena is free today

Open Superagent

MiniStral 3 (14B Instruct 2512) vs Pixtral Large

MiniStral 3 (14B Instruct 2512) and Pixtral Large are closely matched at 9.8 and 11.5 on the LLM Stats Score.

Mistral AI · Mistral AI · Updated for 2026

Which is better?

MiniStral 3 (14B Instruct 2512) and Pixtral Large are closely matched on the overall LLM Stats Score at 9.8 and 11.5.

In the 1 individual benchmarks reported for both models, Pixtral Large wins 1; this is a narrower head-to-head signal than the composite indexes.

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

Choose MiniStral 3 (14B Instruct 2512)

  • you want the most recent training data — it shipped Dec 2025

Choose Pixtral Large

  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results

At a glance

The differences that matter most.

MiniStral 3 (14B Instruct 2512)
Mistral AI
Pixtral Large
Mistral AI
Core performance indexes
LLM Stats Score
9.8
#289
11.5
#280
Reasoning
11.6
#272
12.8
#264
Cost, coverage & limits
Benchmark wins
0 of 1
1 of 1
Input price
— / M
$2.00 / M
Output price
— / M
$6.00 / M
Context window
—
128,000

Individual benchmarks

4 reported for MiniStral 3 (14B Instruct 2512) · 7 for Pixtral Large

1 shared

MiniStral 3 (14B Instruct 2512) outperforms in 0 benchmarks, while Pixtral Large is better at 1 benchmark (MM-MT-Bench).

Pixtral Large significantly outperforms across most benchmarks.

Tue Oct 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

110.0B diff

Pixtral Large has 110.0B more parameters than MiniStral 3 (14B Instruct 2512), making it 785.7% larger.

Mistral AI
MiniStral 3 (14B Instruct 2512)
14.0Bparameters
Mistral AI
Pixtral Large
124.0Bparameters
14.0B
MiniStral 3 (14B Instruct 2512)
124.0B
Pixtral Large

Context Window

Maximum input and output token capacity

Only Pixtral Large specifies input context (128,000 tokens). Only Pixtral Large specifies output context (128,000 tokens).

Mistral AI
MiniStral 3 (14B Instruct 2512)
Input- tokens
Output- tokens
Mistral AI
Pixtral Large
Input128,000 tokens
Output128,000 tokens
Tue Oct 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both MiniStral 3 (14B Instruct 2512) and Pixtral Large support multimodal inputs.

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

MiniStral 3 (14B Instruct 2512)

Text
Images
Audio
Video

Pixtral Large

Text
Images
Audio
Video

License

Usage and distribution terms

MiniStral 3 (14B Instruct 2512) 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.

MiniStral 3 (14B Instruct 2512)

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

MiniStral 3 (14B Instruct 2512) was released on 2025-12-04, while Pixtral Large was released on 2024-11-18.

MiniStral 3 (14B Instruct 2512) is 13 months newer than Pixtral Large.

MiniStral 3 (14B Instruct 2512)

Dec 4, 2025

10 months ago

1.0yr newer
Pixtral Large

Nov 18, 2024

1.9 years ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against MiniStral 3 (14B Instruct 2512) and Pixtral Large side-by-side, then vote on the output you prefer.

MiniStral 3 (14B Instruct 2512)
✓ Preferred
Pixtral Large
Open in Playground

FAQ

Common questions about MiniStral 3 (14B Instruct 2512) vs Pixtral Large.

Which is better, MiniStral 3 (14B Instruct 2512) or Pixtral Large?

MiniStral 3 (14B Instruct 2512) and Pixtral Large are closely matched on the LLM Stats Score at 9.8 and 11.5. MiniStral 3 (14B Instruct 2512) 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 MiniStral 3 (14B Instruct 2512) compare to Pixtral Large in benchmarks?

MiniStral 3 (14B Instruct 2512) scores MATH: 90.4%, Wild Bench: 68.5%, Arena Hard: 55.1%, MM-MT-Bench: 8.5%. Pixtral Large scores AI2D: 93.8%, DocVQA: 93.3%, ChartQA: 88.1%, VQAv2: 80.9%, MM-MT-Bench: 74.0%.

What are the context window sizes for MiniStral 3 (14B Instruct 2512) and Pixtral Large?

MiniStral 3 (14B Instruct 2512) supports an unknown number of 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 MiniStral 3 (14B Instruct 2512) and Pixtral Large?

Key differences include LLM Stats Score (9.8 vs 11.5), 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