Back to Models
DeepSeekProprietary

DeepSeek V3.2 Speciale

DeepSeek V3.2 Speciale, developed by DeepSeek-AI, is a reasoning-focused foundation model with high computational capability. By relaxing output limits, it enhances complex reasoning abilities and achieves gold medal-level performance in top-level competitive programming such as the International Mathematical Olympiad and Informatics Olympiad.

Parameters

Undisclosed

Context Window

License

https://github.com/deepseek-ai/deepseek-LLM/blob/main/LICENSE-MODEL

Release Date

2025-12-01

API Pricing

API pricing for this model is not yet available

Strengths

  • Extremely high complex reasoning ability
  • Strong in competitive programming
  • Performance surpassing GPT-5

Weaknesses

  • Not compatible with tool calling
  • Requires high computational resources
  • Lack of general-purpose feature expansion

Use Cases

  • Solving difficult mathematical problems
  • Advanced code generation
  • Competitive programming preparation

Deep Analysis

Parameters

685B MoE

Arena Elo

1361

#7 overall

AIME 2025

96.0%

HMMT Feb 2025

99.2%

Codeforces

2701

IMO 2025

Gold Medal

Release Date

December 1, 2025

Strengths

  • IMO 2025 and IOI 2025 gold medals
  • Surpasses GPT-5 on multiple benchmarks
  • Fully open-source MIT
  • #7 on Chatbot Arena

Weaknesses

  • High token consumption (23-77k per query)
  • Retired from DeepSeek API
  • Slower due to extended reasoning
  • Weaker on general conversational tasks

Competitor Comparison

ModelArenaGPQAPrice
GPT-5 High~138085.7%$2.50/$15
Gemini 3.0 Pro~138991.9%
DeepSeek-V3.2133482.4%$0.28/$0.42

DeepSeek V3.2 Speciale is the most powerful reasoning model. IMO/IOI gold medals, 96% AIME, #7 Arena Elo 1361.

Sources

Analysis generated: 2026-05-24