readable AI benchmarks (simplified)
OpenAI
GPT-5 nano (Medium)
GPT-5 nano (Medium) has a Quality Score of 24.8, ranking 173rd among 238 scored models. Per 1M tokens, pricing is $0.050 input, $0.400 output, and $0.0050 cached input. It has a 400k token context window. Its Reliability Score is 37.1, ranking 176th among 245 scored models, below average (total average: 46.4). Its Value Score is 23.2, low compared with the total Value average of 28.3.
Quality Score24.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score23.2
Factual reliability37.1
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 400k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $0.050
- Output
- $0.400
- Cached Input
- $0.0050
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 12.5
- Omniscience (native net)
- -25.8
- Correct
- 17.6%
- Blended price
- $0.054
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 61.0%
Correct 17.6%Incorrect 43.4%Partial / not attempted 39.1%
Artificial Analysis benchmarks legacy records
- Humanity’s Last Exam
- 9%
- GPQA Diamond
- 67%
- CritPt
- 0%
- AA-LCR
- 44%
Similar models
- GPT-6 Luna (Low)OpenAIQuality Score 25.3Value Score 23.1
- o3-mini (High)OpenAIQuality Score 19.8Value Score 13.8
- GPT-5.4 mini (Medium)OpenAIQuality Score 29.7Value Score 21.9
- GPT-6 Luna (Medium)OpenAIQuality Score 30.8Value Score 28.2
- GPT-5.4 nano (Medium)OpenAIQuality Score 30.5Value Score 26.0
- GPT-5.6 Luna (Low)OpenAIQuality Score 31.8Value Score 27.2