Model Comparison

DeepSeek-V3.2 (Thinking) vs Ministral 3 (8B Reasoning 2512)

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks. Ministral 3 (8B Reasoning 2512) is 2.1x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

DeepSeek-V3.2 (Thinking) outperforms in 3 benchmarks (AIME 2025, GPQA, LiveCodeBench), while Ministral 3 (8B Reasoning 2512) is better at 0 benchmarks.

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks.

Thu Apr 16 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Ministral 3 (8B Reasoning 2512) costs less

For input processing, DeepSeek-V3.2 (Thinking) ($0.28/1M tokens) is 1.9x more expensive than Ministral 3 (8B Reasoning 2512) ($0.15/1M tokens).

For output processing, DeepSeek-V3.2 (Thinking) ($0.42/1M tokens) is 2.8x more expensive than Ministral 3 (8B Reasoning 2512) ($0.15/1M tokens).

In conclusion, DeepSeek-V3.2 (Thinking) is more expensive than Ministral 3 (8B Reasoning 2512).*

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

Lowest available price from all providers
Thu Apr 16 2026 • llm-stats.com
DeepSeek
DeepSeek-V3.2 (Thinking)
Input tokens$0.28
Output tokens$0.42
Best providerDeepSeek
Mistral AI
Ministral 3 (8B Reasoning 2512)
Input tokens$0.15
Output tokens$0.15
Best providerMistral
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

677.0B diff

DeepSeek-V3.2 (Thinking) has 677.0B more parameters than Ministral 3 (8B Reasoning 2512), making it 8462.5% larger.

DeepSeek
DeepSeek-V3.2 (Thinking)
685.0Bparameters
Mistral AI
Ministral 3 (8B Reasoning 2512)
8.0Bparameters
685.0B
DeepSeek-V3.2 (Thinking)
8.0B
Ministral 3 (8B Reasoning 2512)

Context Window

Maximum input and output token capacity

Ministral 3 (8B Reasoning 2512) accepts 262,100 input tokens compared to DeepSeek-V3.2 (Thinking)'s 131,072 tokens. Ministral 3 (8B Reasoning 2512) can generate longer responses up to 262,100 tokens, while DeepSeek-V3.2 (Thinking) is limited to 65,536 tokens.

DeepSeek
DeepSeek-V3.2 (Thinking)
Input131,072 tokens
Output65,536 tokens
Mistral AI
Ministral 3 (8B Reasoning 2512)
Input262,100 tokens
Output262,100 tokens
Thu Apr 16 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Ministral 3 (8B Reasoning 2512) supports multimodal inputs, whereas DeepSeek-V3.2 (Thinking) does not.

Ministral 3 (8B Reasoning 2512) can handle both text and other forms of data like images, making it suitable for multimodal applications.

DeepSeek-V3.2 (Thinking)

Text
Images
Audio
Video

Ministral 3 (8B Reasoning 2512)

Text
Images
Audio
Video

License

Usage and distribution terms

DeepSeek-V3.2 (Thinking) is licensed under MIT, while Ministral 3 (8B Reasoning 2512) uses Apache 2.0.

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

DeepSeek-V3.2 (Thinking)

MIT

Open weights

Ministral 3 (8B Reasoning 2512)

Apache 2.0

Open weights

Release Timeline

When each model was launched

DeepSeek-V3.2 (Thinking) was released on 2025-12-01, while Ministral 3 (8B Reasoning 2512) was released on 2025-12-04.

Ministral 3 (8B Reasoning 2512) is 0 month newer than DeepSeek-V3.2 (Thinking).

DeepSeek-V3.2 (Thinking)

Dec 1, 2025

4 months ago

Ministral 3 (8B Reasoning 2512)

Dec 4, 2025

4 months ago

3d 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

DeepSeek-V3.2 (Thinking) is available from DeepSeek. Ministral 3 (8B Reasoning 2512) is available from Mistral AI.

DeepSeek-V3.2 (Thinking)

deepseek logo
DeepSeek
Input Price:Input: $0.28/1MOutput Price:Output: $0.42/1M

Ministral 3 (8B Reasoning 2512)

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

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

DeepSeek
Higher AIME 2025 score (93.1% vs 78.7%)
Higher GPQA score (82.4% vs 66.8%)
Higher LiveCodeBench score (83.3% vs 61.6%)
Mistral AI
Larger context window (262,100 tokens)
Supports multimodal inputs
Less expensive input tokens
Less expensive output tokens

Detailed Comparison

AI Model Comparison Table
Feature
DeepSeek
DeepSeek-V3.2 (Thinking)
Mistral AI
Ministral 3 (8B Reasoning 2512)

FAQ

Common questions about DeepSeek-V3.2 (Thinking) vs Ministral 3 (8B Reasoning 2512)

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks. DeepSeek-V3.2 (Thinking) is made by DeepSeek and Ministral 3 (8B Reasoning 2512) is made by Mistral AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
DeepSeek-V3.2 (Thinking) scores AIME 2025: 93.1%, HMMT 2025: 90.2%, MMLU-Pro: 85.0%, LiveCodeBench: 83.3%, GPQA: 82.4%. Ministral 3 (8B Reasoning 2512) scores AIME 2024: 86.0%, AIME 2025: 78.7%, GPQA: 66.8%, LiveCodeBench: 61.6%.
Ministral 3 (8B Reasoning 2512) is 1.9x cheaper for input tokens. DeepSeek-V3.2 (Thinking) costs $0.28/M input and $0.42/M output via deepseek. Ministral 3 (8B Reasoning 2512) costs $0.15/M input and $0.15/M output via mistral.
DeepSeek-V3.2 (Thinking) supports 131K tokens and Ministral 3 (8B Reasoning 2512) supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (131K vs 262K), input pricing ($0.28 vs $0.15/M), multimodal support (no vs yes), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.
DeepSeek-V3.2 (Thinking) is developed by DeepSeek and Ministral 3 (8B Reasoning 2512) is developed by Mistral AI.