The AI arena is free today

Open Superagent

DeepSeek-V3.2-Speciale vs Devstral Medium

DeepSeek-V3.2-Speciale leads the LLM Stats Score 33.9 to 13.6. DeepSeek-V3.2-Speciale is 2.5x cheaper per token.

DeepSeek · Mistral AI · Updated for 2026

Which is better?

DeepSeek-V3.2-Speciale leads the overall LLM Stats Score 33.9 to 13.6, ranking #102 overall.

In the 1 individual benchmarks reported for both models, DeepSeek-V3.2-Speciale wins 1; this is a narrower head-to-head signal than the composite indexes.

On price, DeepSeek-V3.2-Speciale is roughly 2.5x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

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

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

Choose DeepSeek-V3.2-Speciale

  • overall performance matters — it scores 33.9 and ranks #102 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • cost matters — it's about 2.5x cheaper per token
  • you process long inputs — it offers a 131,072 token context window
  • you want the most recent training data — it shipped Dec 2025
  • you need open weights you can self-host or fine-tune

Choose Devstral Medium

  • you want predictable pricing at $0.40/M input and $2.00/M output

At a glance

The differences that matter most.

Core performance indexes
33.9
#102
13.6
#249
32.5
#109
13.5
#242
18.5
#117
5.3
#206
Cost, coverage & limits
Benchmark wins
1 of 1
0 of 1
Input price
$0.28 / M
$0.40 / M
Output price
$0.42 / M
$2.00 / M
Context window
131,072
128,000

Individual benchmarks

8 reported for DeepSeek-V3.2-Speciale · 1 for Devstral Medium

1 shared

DeepSeek-V3.2-Speciale outperforms in 1 benchmarks (SWE-Bench Verified), while Devstral Medium is better at 0 benchmarks.

DeepSeek-V3.2-Speciale significantly outperforms across most benchmarks.

Wed Sep 23 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

DeepSeek-V3.2-Speciale costs less

For input processing, DeepSeek-V3.2-Speciale ($0.28/1M tokens) is 1.4x cheaper than Devstral Medium ($0.40/1M tokens).

For output processing, DeepSeek-V3.2-Speciale ($0.42/1M tokens) is 4.8x cheaper than Devstral Medium ($2.00/1M tokens).

In conclusion, Devstral Medium is more expensive than DeepSeek-V3.2-Speciale.*

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

Lowest available price from all providers
Wed Sep 23 2026 • llm-stats.com
DeepSeek
DeepSeek-V3.2-Speciale
Input tokens$0.28
Output tokens$0.42
Best providerDeepSeek
Mistral AI
Devstral Medium
Input tokens$0.40
Output tokens$2.00
Best providerMistral
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

DeepSeek-V3.2-Speciale accepts 131,072 input tokens compared to Devstral Medium's 128,000 tokens. DeepSeek-V3.2-Speciale can generate longer responses up to 131,072 tokens, while Devstral Medium is limited to 128,000 tokens.

DeepSeek
DeepSeek-V3.2-Speciale
Input131,072 tokens
Output131,072 tokens
Mistral AI
Devstral Medium
Input128,000 tokens
Output128,000 tokens
Wed Sep 23 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V3.2-Speciale is licensed under MIT, while Devstral Medium uses a proprietary license.

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

DeepSeek-V3.2-Speciale

MIT

Open weights

Devstral Medium

Proprietary

Closed source

Release Timeline

When each model was launched

DeepSeek-V3.2-Speciale was released on 2025-12-01, while Devstral Medium was released on 2025-07-10.

DeepSeek-V3.2-Speciale is 5 months newer than Devstral Medium.

DeepSeek-V3.2-Speciale

Dec 1, 2025

9 months ago

4mo newer
Devstral Medium

Jul 10, 2025

1.2 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

Provider Availability

DeepSeek-V3.2-Speciale is available from DeepSeek. Devstral Medium is available from Mistral AI.

DeepSeek-V3.2-Speciale

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

Devstral Medium

mistral logo
Mistral
Input Price:Input: $0.40/1MOutput Price:Output: $2.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against DeepSeek-V3.2-Speciale and Devstral Medium side-by-side, then vote on the output you prefer.

DeepSeek-V3.2-Speciale
✓ Preferred
Devstral Medium
Open in Playground

FAQ

Common questions about DeepSeek-V3.2-Speciale vs Devstral Medium.

Which is better, DeepSeek-V3.2-Speciale or Devstral Medium?

DeepSeek-V3.2-Speciale leads the LLM Stats Score 33.9 to 13.6. DeepSeek-V3.2-Speciale is made by DeepSeek and Devstral Medium 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 DeepSeek-V3.2-Speciale compare to Devstral Medium in benchmarks?

DeepSeek-V3.2-Speciale scores HMMT 2025: 99.2%, AIME 2025: 96.0%, CodeForces: 90.0%, t2-bench: 80.3%, SWE-Bench Verified: 73.1%. Devstral Medium scores SWE-Bench Verified: 61.6%.

Is DeepSeek-V3.2-Speciale cheaper than Devstral Medium?

DeepSeek-V3.2-Speciale is 1.4x cheaper for input tokens. DeepSeek-V3.2-Speciale costs $0.28/M input and $0.42/M output via deepseek. Devstral Medium costs $0.40/M input and $2.00/M output via mistral.

What are the context window sizes for DeepSeek-V3.2-Speciale and Devstral Medium?

DeepSeek-V3.2-Speciale supports 131K tokens and Devstral Medium 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 DeepSeek-V3.2-Speciale and Devstral Medium?

Key differences include LLM Stats Score (33.9 vs 13.6), context window (131K vs 128K), input pricing ($0.28 vs $0.40/M), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V3.2-Speciale and Devstral Medium?

DeepSeek-V3.2-Speciale is developed by DeepSeek and Devstral Medium is developed by Mistral AI.