DeepSeek V4 Pro (Non-reasoning)
Intelligence
39.3
#89/523
Coding
38.4
#65/429
Math
—
Speed
—
Pricing
—
DeepSeek V4 Pro (Non-reasoning) is DeepSeek’s latest model designed for advanced data processing tasks. It features an Intelligence Index of 39.3 and a Coding Index of 38.4, making it suitable for professional users who require efficient data handling.
When to Use DeepSeek V4 Pro (Non-reasoning)
✓ Best For
- Data analysis and reporting
- Software development assistance
- Automated content generation
✗ Not Ideal For
- Real-time applications due to 0 tok/sec speed
- Mathematical problem solving, as Math Index is not available
How DeepSeek V4 Pro (Non-reasoning) Compares
Intelligence Index · Higher is better
AlibabaMiniMaxDeepSeekGoogleMistral
Benchmark Profile
Coding Index
AnthropicKimiDeepSeekOpenAI
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (9)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 39.3 | |
| Coding Index | 38.4 | |
| GPQA | 717% | |
| HLE | 77% | |
| SciCode | 42.4% | |
| IFBench | 45.8% | |
| LCR | 45% | |
| TerminalBench Hard | 36.4% | |
| Tau2 | 91.2% |
Data: Artificial Analysis · Updated: April 30, 2026
Frequently Asked Questions (14)
When was DeepSeek V4 Pro (Non-reasoning) released?
DeepSeek V4 Pro (Non-reasoning) was released on April 24, 2026.
Who created DeepSeek V4 Pro (Non-reasoning)?
DeepSeek V4 Pro (Non-reasoning) was created by DeepSeek.
How intelligent is DeepSeek V4 Pro (Non-reasoning)?
DeepSeek V4 Pro (Non-reasoning) scores 39 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 23).
How verbose is DeepSeek V4 Pro (Non-reasoning)?
When evaluated on the Intelligence Index, DeepSeek V4 Pro (Non-reasoning) generated 14M output tokens, which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 10M).
Is DeepSeek V4 Pro (Non-reasoning) a reasoning model?
No, DeepSeek V4 Pro (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does DeepSeek V4 Pro (Non-reasoning) support?
DeepSeek V4 Pro (Non-reasoning) supports text input.
What output modalities does DeepSeek V4 Pro (Non-reasoning) support?
DeepSeek V4 Pro (Non-reasoning) supports text output.
Can DeepSeek V4 Pro (Non-reasoning) process images?
No, DeepSeek V4 Pro (Non-reasoning) does not support image input. It can only process text.
Is DeepSeek V4 Pro (Non-reasoning) multimodal?
No, DeepSeek V4 Pro (Non-reasoning) is not multimodal. It only supports text input.
What is the context window of DeepSeek V4 Pro (Non-reasoning)?
DeepSeek V4 Pro (Non-reasoning) has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
Is DeepSeek V4 Pro (Non-reasoning) open source?
Yes, DeepSeek V4 Pro (Non-reasoning) is open weights. The model weights are publicly available.
How does DeepSeek V4 Pro (Non-reasoning) perform on benchmarks?
DeepSeek V4 Pro (Non-reasoning) achieves a score of 39 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Is DeepSeek V4 Pro (Non-reasoning) available via API?
DeepSeek V4 Pro (Non-reasoning) is an open weights model that can be self-hosted.
Where can I use DeepSeek V4 Pro (Non-reasoning)?
DeepSeek V4 Pro (Non-reasoning) is an open weights model that can be downloaded and self-hosted.
