readable AI benchmarks (simplified)
DeepSeek
DeepSeek V4 Flash 0420 (Non-reasoning)
DeepSeek V4 Flash 0420 (Non-reasoning) has a Quality Score of 28.5, ranking 89th among 139 scored models. Per 1M tokens, pricing is $0.094 input, $0.188 output, and $0.019 cached input. It has a 1M token context window. Its Reliability Score is 28.0, ranking 99th among 139 scored models, below average (total average: 40.0). Its Value Score is 26.7, around average compared with the total Value average of 30.0.
Quality Score28.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score26.7
Factual reliability28.0
Cache Discount80%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.094
- Output
- $0.188
- Cached Input
- $0.019
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 18.9
- Coding
- not available
- Agentic
- not available
- Omniscience
- -44.0
- Correct
- 26.0%
- Blended price
- $0.051
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 96.0%
Correct 26.0%Incorrect 70.0%Partial / not attempted 4.0%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 8%
- GPQA Diamond
- 72%
- CritPt
- 0%
- AA-Omniscience
- 28%
- AA-LCR
- 42%
Similar models
- DeepSeek V4 Pro 0424 (Non-reasoning)DeepSeekQuality Score 33.6Value Score 28.6
- DeepSeek V4 FlashDeepSeekQuality Score 36.0Value Score 33.5
- DeepSeek V4.1 Flash (Non-reasoning)DeepSeekQuality Score 41.4Value Score 35.2
- DeepSeek V3.2 Exp (Reasoning)DeepSeekQuality Score 30.0Value Score 26.6
- DeepSeek V3.1 Terminus (Reasoning)DeepSeekQuality Score 29.8Value Score 19.5
- DeepSeek V3.1 (Reasoning)DeepSeekQuality Score 28.0Value Score 20.5