DownloadDeepSeek-V3.2-Speciale is the high-compute, ultra-reasoning variant of DeepSeek-V3.2, designed specifically to push the boundaries of mathematical, logical, and algorithmic intelligence. It builds on the DeepSeek Sparse Attention (DSA) framework, delivering dramatically improved long-context efficiency while preserving full model quality. Unlike the standard version, Speciale is tuned exclusively for deep reasoning and therefore does not support tool-calling, focusing its full capacity on pure cognitive performance. The model uses a scaled reinforcement learning framework that allows it to surpass GPT-5 in several evaluations and reach reasoning performance comparable to Gemini-3.0-Pro. DeepSeek-V3.2-Speciale contributed to gold-medal solutions in the 2025 IMO, IOI, ICPC World Finals, and CMO, demonstrating its ability to handle elite-level problem solving. It is released under the MIT license and includes curated benchmark solutions for community verification and analysis.
Features
- High-compute variant optimized solely for deep reasoning (no tool-calling)
- Achieves GPT-5–surpassing performance in several reasoning benchmarks
- Demonstrates reasoning on par with Gemini-3.0-Pro
- Built using a scaled reinforcement learning post-training framework
- Used to generate gold-medal solutions for IMO, IOI, ICPC, and CMO 2025
- Fully open-source under the MIT License
- Shares architecture with V3.2/Exp models for seamless integration and deployment
- Powered by DeepSeek Sparse Attention (DSA) for efficient long-context computation
Project Samples
