DeepSeek
DeepSeek V4 Flash (Non-reasoning)
Quality Score25.5
Value Score31.6
Reliability28.0
Cache Discount25%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.094
- Output
- $0.195
- Cached Input
- $0.070
- Cached Output
- not available
- Cost per task
- not available
Capability
- Intelligence
- 29.3
- Coding
- not available
- Agentic
- not available
- Omniscience
- -44.0
- Correct
- 26.0%
- Blended price
- $0.087
Answer outcomes
Correct 26.0%Incorrect 70.0%Abstained 4.0%
Artificial Analysis benchmarks
- SciCode
- 37%
- Humanity’s Last Exam
- 8%
- GPQA Diamond
- 72%
- CritPt
- 0%
- AA-Omniscience
- 28%
- AA-LCR
- 37%
Similar models
- DeepSeek V4 Pro (Non-reasoning)DeepSeekQuality Score 31.8Value Score 33.5
- DeepSeek V4 Pro (Reasoning, High Effort)DeepSeekQuality Score 50.6Value Score 46.0
- DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeekQuality Score 52.0Value Score 47.6
- DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeekQuality Score 55.1Value Score 50.5
- DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeekQuality Score 63.3Value Score 47.9
- MiMo-V2.5-Pro (Non-reasoning)XiaomiQuality Score 26.9Value Score 29.6