readable AI benchmarks (simplified)
DeepSeek
DeepSeek V4.1 Flash (max)
DeepSeek V4.1 Flash (max) has a Quality Score of 49.5, ranking 47th among 291 scored models. Per 1M tokens, pricing is $0.300 input, $1.20 output, and $0.0060 cached input. It has a 1M token context window. Its Reliability Score is 47.4, ranking 80th among 291 scored models, above average (total average: 35.7). Its Value Score is 43.9, high compared with the total Value average of 29.0.
Quality Score49.5coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score43.9
Reliability47.4
Cache Discount98%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.300
- Output
- $1.20
- Cached Input
- $0.0060
- Cache write
- not available
- Cost per task
- $0.265
Capability
- Intelligence
- 39.5
- Coding
- not available
- Agentic
- not available
- Omniscience
- -5.3
- Correct
- 46.4%
- Blended price
- $0.184
Answer outcomes
Attempt rate: 98.1%
Correct 46.4%Incorrect 51.7%Abstained 1.9%
Artificial Analysis benchmarks
- GDPval-AA v2
- 57%
- SciCode
- 52%
- Humanity’s Last Exam
- 39%
- CritPt
- 14%
- AA-Omniscience
- 47%
- AA-LCR
- 84%
Similar models
- DeepSeek V4 Pro 0813 (max)DeepSeekQuality Score 51.4Value Score 36.5
- DeepSeek V4 Flash 0731 (max)DeepSeekQuality Score 41.5Value Score 37.3
- DeepSeek V4 Flash Vision (max)DeepSeekQuality Score 39.8Value Score 37.1
- DeepSeek V4 Pro (max)DeepSeekQuality Score 42.2Value Score 36.2
- DeepSeek V4 Pro (high)DeepSeekQuality Score 41.2Value Score 35.3
- DeepSeek V4 Pro (Non-reasoning)DeepSeekQuality Score 26.9Value Score 24.7