Model Comparison

DeepSeek-V3.2 (Thinking) vs Mistral Small 3 24B InstructWhich is better in 2026?

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks. Mistral Small 3 24B Instruct is 3.6x cheaper per token.

Verdict: DeepSeek-V3.2 (Thinking) vs Mistral Small 3 24B Instruct — which is better?

DeepSeek-V3.2 (Thinking) (by DeepSeek) and Mistral Small 3 24B Instruct (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.

DeepSeek-V3.2 (Thinking) outperforms in 2 benchmarks (GPQA, MMLU-Pro), while Mistral Small 3 24B Instruct is better at 0 benchmarks. DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks.

On price, Mistral Small 3 24B Instruct is roughly 3.6x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

DeepSeek-V3.2 (Thinking) also accepts a larger context window (131,072 input tokens), making it the stronger choice for long documents and large codebases.

Choose DeepSeek-V3.2 (Thinking) if…

  • you want the strongest raw capability — it leads on 2 of 2 shared benchmarks
  • you process long inputs — it offers a 131,072 token context window
  • you want the most recent training data — it shipped Dec 2025

Choose Mistral Small 3 24B Instruct if…

  • cost matters — it's about 3.6x cheaper per token

Performance Benchmarks

Comparative analysis across standard metrics

2 benchmarks

DeepSeek-V3.2 (Thinking) outperforms in 2 benchmarks (GPQA, MMLU-Pro), while Mistral Small 3 24B Instruct is better at 0 benchmarks.

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

Sat Jun 27 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Mistral Small 3 24B Instruct costs less

For input processing, DeepSeek-V3.2 (Thinking) ($0.28/1M tokens) is 4.0x more expensive than Mistral Small 3 24B Instruct ($0.07/1M tokens).

For output processing, DeepSeek-V3.2 (Thinking) ($0.42/1M tokens) is 3.0x more expensive than Mistral Small 3 24B Instruct ($0.14/1M tokens).

In conclusion, DeepSeek-V3.2 (Thinking) is more expensive than Mistral Small 3 24B Instruct.*

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

Lowest available price from all providers
Sat Jun 27 2026 • llm-stats.com
DeepSeek
DeepSeek-V3.2 (Thinking)
Input tokens$0.28
Output tokens$0.42
Best providerDeepSeek
Mistral AI
Mistral Small 3 24B Instruct
Input tokens$0.07
Output tokens$0.14
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

661.0B diff

DeepSeek-V3.2 (Thinking) has 661.0B more parameters than Mistral Small 3 24B Instruct, making it 2754.2% larger.

DeepSeek
DeepSeek-V3.2 (Thinking)
685.0Bparameters
Mistral AI
Mistral Small 3 24B Instruct
24.0Bparameters
685.0B
DeepSeek-V3.2 (Thinking)
24.0B
Mistral Small 3 24B Instruct

Context Window

Maximum input and output token capacity

DeepSeek-V3.2 (Thinking) accepts 131,072 input tokens compared to Mistral Small 3 24B Instruct's 32,000 tokens. DeepSeek-V3.2 (Thinking) can generate longer responses up to 65,536 tokens, while Mistral Small 3 24B Instruct is limited to 32,000 tokens.

DeepSeek
DeepSeek-V3.2 (Thinking)
Input131,072 tokens
Output65,536 tokens
Mistral AI
Mistral Small 3 24B Instruct
Input32,000 tokens
Output32,000 tokens
Sat Jun 27 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V3.2 (Thinking) is licensed under MIT, while Mistral Small 3 24B Instruct 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

Mistral Small 3 24B Instruct

Apache 2.0

Open weights

Release Timeline

When each model was launched

DeepSeek-V3.2 (Thinking) was released on 2025-12-01, while Mistral Small 3 24B Instruct was released on 2025-01-30.

DeepSeek-V3.2 (Thinking) is 10 months newer than Mistral Small 3 24B Instruct.

DeepSeek-V3.2 (Thinking)

Dec 1, 2025

6 months ago

10mo newer
Mistral Small 3 24B Instruct

Jan 30, 2025

1.4 years ago

Knowledge Cutoff

When training data ends

Mistral Small 3 24B Instruct has a documented knowledge cutoff of 2023-10-01, while DeepSeek-V3.2 (Thinking)'s cutoff date is not specified.

We can confirm Mistral Small 3 24B Instruct's training data extends to 2023-10-01, but cannot make a direct comparison without DeepSeek-V3.2 (Thinking)'s cutoff date.

DeepSeek-V3.2 (Thinking)

—

Mistral Small 3 24B Instruct

Oct 2023

Provider Availability

DeepSeek-V3.2 (Thinking) is available from DeepSeek. Mistral Small 3 24B Instruct is available from DeepInfra, Mistral AI.

DeepSeek-V3.2 (Thinking)

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

Mistral Small 3 24B Instruct

deepinfra logo
Deepinfra
Input Price:Input: $0.07/1MOutput Price:Output: $0.14/1M
mistral logo
Mistral
Input Price:Input: $0.10/1MOutput Price:Output: $0.30/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

DeepSeek
Larger context window (131,072 tokens)
Higher GPQA score (82.4% vs 45.3%)
Higher MMLU-Pro score (85.0% vs 66.3%)
Mistral AI
Less expensive input tokens
Less expensive output tokens

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against DeepSeek-V3.2 (Thinking) and Mistral Small 3 24B Instruct side-by-side, then vote on the output you prefer.

DeepSeek-V3.2 (Thinking)
✓ Preferred
Mistral Small 3 24B Instruct
Open in Playground
AI Model Comparison Table
Feature
DeepSeek
DeepSeek-V3.2 (Thinking)
Mistral AI
Mistral Small 3 24B Instruct

FAQ

Common questions about DeepSeek-V3.2 (Thinking) vs Mistral Small 3 24B Instruct.

Which is better, DeepSeek-V3.2 (Thinking) or Mistral Small 3 24B Instruct?

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks. DeepSeek-V3.2 (Thinking) is made by DeepSeek and Mistral Small 3 24B Instruct is made by Mistral AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does DeepSeek-V3.2 (Thinking) compare to Mistral Small 3 24B Instruct in benchmarks?

DeepSeek-V3.2 (Thinking) scores AIME 2025: 93.1%, HMMT 2025: 90.2%, MMLU-Pro: 85.0%, LiveCodeBench: 83.3%, GPQA: 82.4%. Mistral Small 3 24B Instruct scores Arena Hard: 87.6%, HumanEval: 84.8%, MT-Bench: 83.5%, IFEval: 82.9%, MATH: 70.6%.

Is DeepSeek-V3.2 (Thinking) cheaper than Mistral Small 3 24B Instruct?

Mistral Small 3 24B Instruct is 4.0x cheaper for input tokens. DeepSeek-V3.2 (Thinking) costs $0.28/M input and $0.42/M output via deepseek. Mistral Small 3 24B Instruct costs $0.07/M input and $0.14/M output via deepinfra.

What are the context window sizes for DeepSeek-V3.2 (Thinking) and Mistral Small 3 24B Instruct?

DeepSeek-V3.2 (Thinking) supports 131K tokens and Mistral Small 3 24B Instruct supports 32K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between DeepSeek-V3.2 (Thinking) and Mistral Small 3 24B Instruct?

Key differences include context window (131K vs 32K), input pricing ($0.28 vs $0.07/M), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V3.2 (Thinking) and Mistral Small 3 24B Instruct?

DeepSeek-V3.2 (Thinking) is developed by DeepSeek and Mistral Small 3 24B Instruct is developed by Mistral AI.

Related comparisons