News
DeepSeek-V3.2 Release 2025/12/01
News
🔹 DeepSeek-V3.2: Official successor to V3.2-Exp. Now live on App, Web & API.
DeepSeek-V3.2 Release 2025/12/01
🔹 DeepSeek-V3.2-Speciale: Pushing the boundaries of reasoning capabilities. API-only for now.
🚀 Launching DeepSeek-V3.2 & DeepSeek-V3.2-Speciale — Reasoning-first models built for agents!
📄 Tech report: https://huggingface.co/deepseek-ai/DeepSeek-V3.2/resolve/main/assets/paper.pdf
🔹 DeepSeek-V3.2: Official successor to V3.2-Exp. Now live on App, Web & API.
🔹 V3.2: Balanced inference vs. length. Your daily driver at GPT-5 level performance.
🔹 DeepSeek-V3.2: Official successor to V3.2-Exp. Now live on App, Web & API.
🔹 V3.2-Speciale: Maxed-out reasoning capabilities. Rivals Gemini-3.0-Pro.
🔹 DeepSeek-V3.2-Speciale: Pushing the boundaries of reasoning capabilities. API-only for now.
🥇 Gold-Medal Performance: V3.2-Speciale attains gold-level results in IMO, CMO, ICPC World Finals & IOI 2025.
🔹 DeepSeek-V3.2-Speciale: Pushing the boundaries of reasoning capabilities. API-only for now.
📄 Tech report: https://huggingface.co/deepseek-ai/DeepSeek-V3.2/resolve/main/assets/paper.pdf
🔹 Introduces a new massive agent training data synthesis method covering 1,800+ environments & 85k+ complex instructions.
📄 Tech report: https://huggingface.co/deepseek-ai/DeepSeek-V3.2/resolve/main/assets/paper.pdf
🔹 DeepSeek-V3.2 is our first model to integrate thinking directly into tool-use, and also supports tool-use in both thinking and non-thinking modes.
🔹 V3.2: Balanced inference vs. length. Your daily driver at GPT-5 level performance.
🔹 V3.2: Same usage pattern as V3.2-Exp.
🔹 V3.2: Balanced inference vs. length. Your daily driver at GPT-5 level performance.
🔹 V3.2-Speciale: Served via a temporary endpoint: base_url="https://api.deepseek.com/v3.2_speciale_expires_on_20251215". Same pricing as V3.2, no tool calls, available until Dec 15th, 2025, 15:59 (UTC Time).
🔹 V3.2-Speciale: Maxed-out reasoning capabilities. Rivals Gemini-3.0-Pro.
💡 V3.2 now supports Thinking in Tool-Use — details: https://api-docs.deepseek.com/guides/thinking_mode
🔹 V3.2-Speciale: Maxed-out reasoning capabilities. Rivals Gemini-3.0-Pro.
📦 DeepSeek-V3.2 Model: https://huggingface.co/deepseek-ai/DeepSeek-V3.2
🥇 Gold-Medal Performance: V3.2-Speciale attains gold-level results in IMO, CMO, ICPC World Finals & IOI 2025.
📦 DeepSeek-V3.2-Speciale Model: https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale
🥇 Gold-Medal Performance: V3.2-Speciale attains gold-level results in IMO, CMO, ICPC World Finals & IOI 2025.
