DeepSeek
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)
Quality Score55.1
Value Score50.5
Reliability42.9
Cache Discount97%
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.440
- Output
- $1.32
- Cached Input
- $0.014
- Cached Output
- not available
- Cost per task
- $0.112
Capability
- Intelligence
- 51.8
- Coding
- 69.1
- Agentic
- 48.4
- Omniscience
- -14.3
- Correct
- 40.4%
- Blended price
- $0.230
Answer outcomes
Correct 40.4%Incorrect 54.7%Abstained 5.0%
Artificial Analysis benchmarks
- GDPval-AA v2
- 53%
- τ³-Banking
- 39%
- Terminal-Bench v2.1
- 79%
- SciCode
- 50%
- Humanity’s Last Exam
- 39%
- GPQA Diamond
- 91%
- CritPt
- 17%
- AA-Omniscience
- 43%
- AA-LCR
- 74%
Similar models
- DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeekQuality Score 52.0Value Score 47.6
- DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeekQuality Score 63.3Value Score 47.9
- DeepSeek V4 Pro (Reasoning, High Effort)DeepSeekQuality Score 50.6Value Score 46.0
- DeepSeek V4 Pro (Non-reasoning)DeepSeekQuality Score 31.8Value Score 33.5
- DeepSeek V4 Flash (Non-reasoning)DeepSeekQuality Score 25.5Value Score 31.6
- GLM-5.2 (max)Z AIQuality Score 54.9Value Score 40.8