readable AI benchmarks (simplified)
DeepSeek
DeepSeek V4 Flash
DeepSeek V4 Flash has a Quality Score of 36.0, ranking 226th among 572 scored models. Per 1M tokens, pricing is $0.140 input, $0.280 output, and $0.0028 cached input. It accepts text input, outputs text, and has a 1M token context window. Its Reliability Score is 27.9, ranking 354th among 574 scored models, below average (total average: 36.5). Its Value Score is 33.5, around average compared with the total Value average of 31.5.
Quality Score36.0coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score33.5
Factual reliability27.9
Cache Discount98%
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
- $0.140
- Output
- $0.280
- Cached Input
- $0.0028
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 28.7
- Coding
- not available
- Agentic
- not available
- Omniscience
- -44.2
- Correct
- 26.1%
- Blended price
- $0.058
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 96.4%
Correct 26.1%Incorrect 70.3%Partial / not attempted 3.6%
Artificial Analysis benchmarks
- SciCode
- 37%
- Humanity’s Last Exam
- 7%
- GPQA Diamond
- 72%
- CritPt
- 0%
- AA-Omniscience
- 28%
- AA-LCR
- 33%
Similar models
- DeepSeek V4 Pro 0813 (Non-reasoning)DeepSeekQuality Score 37.6Value Score 27.5
- DeepSeek V4 Pro 0424 (Non-reasoning)DeepSeekQuality Score 33.6Value Score 28.6
- DeepSeek V4.1 Flash (Non-reasoning)DeepSeekQuality Score 41.4Value Score 35.2
- DeepSeek V4 Flash 0420 (Non-reasoning)DeepSeekQuality Score 28.5Value Score 26.1
- DeepSeek V3.2 (Non-reasoning)DeepSeekQuality Score 25.6Value Score not available
- DeepSeek V3.1 Terminus (Non-reasoning)DeepSeekQuality Score 24.8Value Score 20.5