readable AI benchmarks (simplified)
OpenAI
GPT-5.4 (Non-reasoning)
GPT-5.4 (Non-reasoning) has a Quality Score of 30.2, ranking 155th among 238 scored models. Per 1M tokens, pricing is $2.50 input, $15.00 output, and $0.250 cached input. It has a 1050k token context window. Its Reliability Score is 42.2, ranking 159th among 245 scored models, below average (total average: 46.4). Its Value Score is 19.2, low compared with the total Value average of 28.3.
Quality Score30.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score19.2
Factual reliability42.2
Cache Discount90%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1050k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $2.50
- Output
- $15.00
- Cached Input
- $0.250
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 18.2
- Omniscience (native net)
- -15.7
- Correct
- 37.4%
- Blended price
- $2.18
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 90.4%
Correct 37.4%Incorrect 53.0%Partial / not attempted 9.6%
Artificial Analysis benchmarks legacy records
- Humanity’s Last Exam
- 11%
- GPQA Diamond
- 75%
- CritPt
- 1%
- AA-LCR
- 58%
Similar models
- GPT-5.2 (Non-reasoning)OpenAIQuality Score 30.4Value Score 19.7
- GPT-5.6 Luna (Non-reasoning)OpenAIQuality Score 26.5Value Score 22.7
- GPT-5.5 (Non-reasoning)OpenAIQuality Score 35.4Value Score 20.8
- GPT-5.1 (Non-reasoning)OpenAIQuality Score 23.0Value Score 15.6
- GPT-5 (Minimal)OpenAIQuality Score 22.3Value Score 15.0
- GPT-6 Luna (Non-reasoning)OpenAIQuality Score 23.3Value Score 21.3