DeepSeek mit Released Dec 1, 2025 Updated
DeepSeek-V3.2 (Non-thinking)
ToolsGuide Scores, rankings, test results and price.
Model summary
Summary
DeepSeek-V3.2 (Non-thinking) is DeepSeek's model, released Dec 1, 2025. It's ranked in 2 categories and does best at text: #116 of 416, with a ToolsGuide Score of 346 against a median of 235.
It also ranks #109 of 147 for coding (258).
Its text and coding score uses votes only, because it has published fewer than two of the tests used for those categories.
It costs $0.28 per million input tokens and $0.42 per million output tokens, below the median text model ($0.43).
Specifications
- Creator
- DeepSeek
- Licence
- mit
- Released
- Dec 1, 2025
- Context window
- 131K tokens
- Input price
- $0.28 / 1M
- Output price
- $0.42 / 1M
- Tests reported
- 0
- Settings ranked
- deepseek-v3.2, deepseek-v3.2-thinking, DeepSeek-V3.2 (Thinking), DeepSeek-V3.2
Model comparison
Against the ten best text models.
Text score
ToolsGuide Score out of 1,000 · Higher is better
Coding score
ToolsGuide Score out of 1,000 · Higher is better
Input price
USD per 1M input tokens · Lower is better
Leaderboards
Where DeepSeek-V3.2 (Non-thinking) sits among the top 20 in each category.
Text
#116 of 416 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model
Coding
#109 of 147 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model
By task
Scored from votes on each kind of prompt alone, on the same 1,000-point scale.
Score against price
Text · the 10 priced models ranked closest · up and to the left is better value
Against its nearest rivals
Text prompts by kind · ToolsGuide Score from votes · hover for values
- DeepSeek-V3.2 (Non-thinking)
- step-3.5-flash
- deepseek-v3.2-exp-thinking
Text
deepseek-v3.2 · hover a bar for its rank
Coding
DeepSeek-V3.2 (Thinking) · hover a bar for its rank
Test results
DeepSeek-V3.2 (Non-thinking) has no published test results yet, so its scores come from votes alone.