readable AI benchmarks (simplified)
DeepSeek
DeepSeek V3.2 (Non-reasoning)
DeepSeek V3.2 (Non-reasoning) has a Quality Score of 25.6, ranking 300th among 551 scored models. Per 1M tokens, pricing is $0.280 input and $0.420 output. It accepts text input, outputs text, and has a 128k token context window. Its Reliability Score is 26.6, ranking 353rd among 553 scored models, below average (total average: 35.6).
Quality Score25.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability26.6
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 128k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.280
- Output
- $0.420
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 16.0
- Coding
- not available
- Agentic
- not available
- Omniscience
- -46.9
- Correct
- 24.0%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 94.9%
Correct 24.0%Incorrect 70.9%Partial / not attempted 5.1%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 11%
- GPQA Diamond
- 75%
- CritPt
- 1%
- AA-Omniscience
- 27%
- AA-LCR
- 46%
Similar models
- DeepSeek V3.1 Terminus (Non-reasoning)DeepSeekQuality Score 24.8Value Score 20.5
- DeepSeek V3.1 (Non-reasoning)DeepSeekQuality Score 24.9Value Score 18.2
- DeepSeek V3.2 Exp (Non-reasoning)DeepSeekQuality Score 23.6Value Score 20.9
- DeepSeek V4 Flash 0420 (Non-reasoning)DeepSeekQuality Score 28.5Value Score 25.9
- DeepSeek V3 0324DeepSeekQuality Score 22.3Value Score 15.9
- DeepSeek V3 (Dec '24)DeepSeekQuality Score 21.1Value Score not available