readable AI benchmarks (simplified)
DeepSeek
DeepSeek V4 Flash 0420 (High)
DeepSeek V4 Flash 0420 (High) has a Quality Score of 31.4, ranking 149th among 239 scored models. Per 1M tokens, pricing is $0.112 input, $0.234 output, and $0.024 cached input. It has a 1M token context window. Its Reliability Score is 38.5, ranking 174th among 246 scored models, below average (total average: 46.4). Its Value Score is 29.1, around average compared with the total Value average of 28.3.
Quality Score31.4coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score29.1
Factual reliability38.5
Cache Discount79%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.112
- Output
- $0.234
- Cached Input
- $0.024
- Cache write
- not available
- Cost per task
- $0.103
Capability
- Intelligence
- 24.4
- Omniscience (native net)
- -23.1
- Correct
- 34.9%
- Blended price
- $0.062
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 92.8%
Correct 34.9%Incorrect 58.0%Partial / not attempted 7.2%
Artificial Analysis benchmarks legacy records
- Legacy GDPval-AA (normalized)
- 25%
- τ³-Banking
- 26%
- SciCode
- 40%
- Humanity’s Last Exam
- 30%
- GPQA Diamond
- 87%
- CritPt
- 3%
- AA-LCR
- 72%
Similar models
- DeepSeek V3.2 (Reasoning)DeepSeekQuality Score 30.1Value Score 26.9
- DeepSeek V4 Pro 0813 (Max)DeepSeekQuality Score 34.9Value Score 25.6
- DeepSeek V4 Pro 0424 (High)DeepSeekQuality Score 37.4Value Score 31.9
- DeepSeek V3.2 Exp (Reasoning)DeepSeekQuality Score 25.5Value Score 22.6
- DeepSeek V4.1 Flash 1017 (High)DeepSeekQuality Score 39.7Value Score 33.7
- DeepSeek V3.1 Terminus (Reasoning)DeepSeekQuality Score 25.8Value Score 16.9