readable AI benchmarks (simplified)
OpenAI
GPT-5 (Medium)
GPT-5 (Medium) has a Quality Score of 33.7, ranking 131st among 238 scored models. Per 1M tokens, pricing is $1.25 input, $10.00 output, and $0.125 cached input. It has a 400k token context window. Its Reliability Score is 44.6, ranking 143rd among 245 scored models, below average (total average: 46.4). Its Value Score is 22.8, low compared with the total Value average of 28.3.
Quality Score33.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score22.8
Factual reliability44.6
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
- $1.25
- Output
- $10.00
- Cached Input
- $0.125
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 22.9
- Omniscience (native net)
- -10.9
- Correct
- 39.5%
- Blended price
- $1.34
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 89.8%
Correct 39.5%Incorrect 50.3%Partial / not attempted 10.2%
Artificial Analysis benchmarks legacy records
- Humanity’s Last Exam
- 25%
- GPQA Diamond
- 84%
- CritPt
- 0%
- AA-LCR
- 76%
Similar models
- GPT-6 Luna (Xhigh)OpenAIQuality Score 33.5Value Score 30.6
- GPT-5.6 Luna (Medium)OpenAIQuality Score 34.2Value Score 29.2
- GPT-6 Luna (High)OpenAIQuality Score 32.5Value Score 29.7
- GPT-5 (Low)OpenAIQuality Score 32.7Value Score 22.1
- GPT-5 mini (Medium)OpenAIQuality Score 32.5Value Score 26.6
- GPT-5.6 Luna (Low)OpenAIQuality Score 31.8Value Score 27.2