Model Comparison

Ministral 3 (14B Reasoning 2512) vs Mistral Small 4Which is better in 2026?

Ministral 3 (14B Reasoning 2512) shows notably better performance in the majority of benchmarks. Ministral 3 (14B Reasoning 2512) is 1.3x cheaper per token.

Verdict: Ministral 3 (14B Reasoning 2512) vs Mistral Small 4 — which is better?

Ministral 3 (14B Reasoning 2512) (by Mistral AI) and Mistral Small 4 (by Mistral AI) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Ministral 3 (14B Reasoning 2512) outperforms in 2 benchmarks (AIME 2025, LiveCodeBench), while Mistral Small 4 is better at 0 benchmarks. Ministral 3 (14B Reasoning 2512) shows notably better performance in the majority of benchmarks.

On price, Ministral 3 (14B Reasoning 2512) is roughly 1.3x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Ministral 3 (14B Reasoning 2512) also accepts a larger context window (262,100 input tokens), making it the stronger choice for long documents and large codebases.

Choose Ministral 3 (14B Reasoning 2512) if…

  • you want the strongest raw capability — it leads on 2 of 3 shared benchmarks
  • cost matters — it's about 1.3x cheaper per token
  • you process long inputs — it offers a 262,100 token context window

Choose Mistral Small 4 if…

  • you want the most recent training data — it shipped Mar 2026

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

Ministral 3 (14B Reasoning 2512) outperforms in 2 benchmarks (AIME 2025, LiveCodeBench), while Mistral Small 4 is better at 0 benchmarks.

Ministral 3 (14B Reasoning 2512) shows notably better performance in the majority of benchmarks.

Mon Jul 27 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Ministral 3 (14B Reasoning 2512) costs less

For input processing, Ministral 3 (14B Reasoning 2512) ($0.20/1M tokens) is 1.3x more expensive than Mistral Small 4 ($0.15/1M tokens).

For output processing, Ministral 3 (14B Reasoning 2512) ($0.20/1M tokens) is 3.0x cheaper than Mistral Small 4 ($0.60/1M tokens).

In conclusion, Mistral Small 4 is more expensive than Ministral 3 (14B Reasoning 2512).*

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

Lowest available price from all providers
Mon Jul 27 2026 • llm-stats.com
Mistral AI
Ministral 3 (14B Reasoning 2512)
Input tokens$0.20
Output tokens$0.20
Best providerMistral
Mistral AI
Mistral Small 4
Input tokens$0.15
Output tokens$0.60
Best providerMistral
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

105.0B diff

Mistral Small 4 has 105.0B more parameters than Ministral 3 (14B Reasoning 2512), making it 750.0% larger.

Mistral AI
Ministral 3 (14B Reasoning 2512)
14.0Bparameters
Mistral AI
Mistral Small 4
119.0Bparameters
14.0B
Ministral 3 (14B Reasoning 2512)
119.0B
Mistral Small 4

Context Window

Maximum input and output token capacity

Ministral 3 (14B Reasoning 2512) accepts 262,100 input tokens compared to Mistral Small 4's 256,000 tokens. Ministral 3 (14B Reasoning 2512) can generate longer responses up to 262,100 tokens, while Mistral Small 4 is limited to 256,000 tokens.

Mistral AI
Ministral 3 (14B Reasoning 2512)
Input262,100 tokens
Output262,100 tokens
Mistral AI
Mistral Small 4
Input256,000 tokens
Output256,000 tokens
Mon Jul 27 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Ministral 3 (14B Reasoning 2512) and Mistral Small 4 support multimodal inputs.

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

Ministral 3 (14B Reasoning 2512)

Text
Images
Audio
Video

Mistral Small 4

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under Apache 2.0.

Both models share the same licensing terms, providing consistent usage rights.

Ministral 3 (14B Reasoning 2512)

Apache 2.0

Open weights

Mistral Small 4

Apache 2.0

Open weights

Release Timeline

When each model was launched

Ministral 3 (14B Reasoning 2512) was released on 2025-12-04, while Mistral Small 4 was released on 2026-03-16.

Mistral Small 4 is 3 months newer than Ministral 3 (14B Reasoning 2512).

Ministral 3 (14B Reasoning 2512)

Dec 4, 2025

7 months ago

Mistral Small 4

Mar 16, 2026

4 months ago

3mo newer

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

Provider Availability

Ministral 3 (14B Reasoning 2512) is available from Mistral AI. Mistral Small 4 is available from Mistral AI.

Ministral 3 (14B Reasoning 2512)

mistral logo
Mistral
Input Price:Input: $0.20/1MOutput Price:Output: $0.20/1M

Mistral Small 4

mistral logo
Mistral
Input Price:Input: $0.15/1MOutput Price:Output: $0.60/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Key Takeaways

Larger context window (262,100 tokens)
Less expensive output tokens
Higher AIME 2025 score (85.0% vs 83.8%)
Higher LiveCodeBench score (64.6% vs 63.6%)
Less expensive input tokens

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Ministral 3 (14B Reasoning 2512) and Mistral Small 4 side-by-side, then vote on the output you prefer.

Ministral 3 (14B Reasoning 2512)
✓ Preferred
Mistral Small 4
Open in Playground
AI Model Comparison Table
Feature
Mistral AI
Ministral 3 (14B Reasoning 2512)
Mistral AI
Mistral Small 4

FAQ

Common questions about Ministral 3 (14B Reasoning 2512) vs Mistral Small 4.

Which is better, Ministral 3 (14B Reasoning 2512) or Mistral Small 4?

Ministral 3 (14B Reasoning 2512) shows notably better performance in the majority of benchmarks. Ministral 3 (14B Reasoning 2512) is made by Mistral AI and Mistral Small 4 is made by Mistral AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Ministral 3 (14B Reasoning 2512) compare to Mistral Small 4 in benchmarks?

Ministral 3 (14B Reasoning 2512) scores AIME 2024: 89.8%, AIME 2025: 85.0%, GPQA: 71.2%, LiveCodeBench: 64.6%. Mistral Small 4 scores AIME 2025: 83.8%, MMLU-Pro: 78.0%, AA-LCR: 71.2%, GPQA: 71.2%, LiveCodeBench: 63.6%.

Is Ministral 3 (14B Reasoning 2512) cheaper than Mistral Small 4?

Mistral Small 4 is 1.3x cheaper for input tokens. Ministral 3 (14B Reasoning 2512) costs $0.20/M input and $0.20/M output via mistral. Mistral Small 4 costs $0.15/M input and $0.60/M output via mistral.

What are the context window sizes for Ministral 3 (14B Reasoning 2512) and Mistral Small 4?

Ministral 3 (14B Reasoning 2512) supports 262K tokens and Mistral Small 4 supports 256K 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 Reasoning 2512) and Mistral Small 4?

Key differences include context window (262K vs 256K), input pricing ($0.20 vs $0.15/M). See the full comparison above for benchmark-by-benchmark results.