DeepSeek-V3.2
DeepSeek-V3.2 is an open-weights AI model from DeepSeek with an index score of 141 (GPT-4 = 100), rank 92 of 217.
141125–157Index score#92 of 217 models
$0.26/ $0.38Price per million tokensinput / output · via OpenRouter
164KContext windowtokens it reads at once
1 Dec 2025Released1 year ago
Where it sitson the frontier
Gemini 2.5 Pro reached this score 8 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workno evidence yet
Novel problemsno evidence yet
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 9 leaderboards
The Model Indexthird-party tests, our method#92of 217 · 141
LMArena · Creative writingcreative writing#91of 360 · 1401LMArena · Instruction followingfollowing detailed instructions#93of 362 · 1421LMArena · Long promptslong, complex requests#93of 340 · 1442LMArena · Mathsmaths questions in chat#95of 346 · 1428LMArena · Codingcoding questions in chat#101of 357 · 1475LMArena · Textoverall chat quality, judged by people#103of 362 · 1425Epoch Capabilities Indexoverall capability from many benchmarks#89of 231 · 146.3LMArena · WebDevbuilding web apps and front ends#100of 133 · 1362Best attop three among current models
Not in the top three among current models on any category we track.
Where to use itprices checked 18 Nov 2026
API providers 6 · per 1M tokens, in / out
Run it yourself
Official weightsdeepseek-ai/DeepSeek-V3.2↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released1 Dec 2025
Announcementapi-docs.deepseek.com ↗
Release entryDeepSeek-V3.2 (+ Speciale)
Scored asDeepSeek-V3.2
Output speed–
Hugging Facedeepseek-ai/DeepSeek-V3.2 ↗