readable AI benchmarks (simplified)
OpenAI
GPT-5.4 mini (Non-reasoning)
GPT-5.4 mini (Non-reasoning) has a Quality Score of 19.2, ranking 202nd among 238 scored models. Per 1M tokens, pricing is $0.750 input, $4.50 output, and $0.075 cached input. It has a 400k token context window. Its Reliability Score is 27.3, ranking 207th among 245 scored models, below average (total average: 46.4). Its Value Score is 14.2, low compared with the total Value average of 28.3.
Quality Score19.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score14.2
Factual reliability27.3
Cache Discount90%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 400k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $0.750
- Output
- $4.50
- Cached Input
- $0.075
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 11.1
- Omniscience (native net)
- -45.4
- Correct
- 25.7%
- Blended price
- $0.653
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 96.7%
Correct 25.7%Incorrect 71.1%Partial / not attempted 3.3%
Artificial Analysis benchmarks legacy records
- Legacy GDPval-AA (normalized)
- 4%
- Humanity’s Last Exam
- 6%
- GPQA Diamond
- 61%
- CritPt
- 0%
- AA-LCR
- 37%
Similar models
- GPT-5.4 nano (Non-reasoning)OpenAIQuality Score 21.5Value Score 18.3
- GPT-5 (Minimal)OpenAIQuality Score 22.3Value Score 15.0
- GPT-5 mini (Minimal)OpenAIQuality Score 16.7Value Score 13.6
- GPT-6 Luna (Non-reasoning)OpenAIQuality Score 23.3Value Score 21.3
- GPT-5.1 (Non-reasoning)OpenAIQuality Score 23.0Value Score 15.6
- GPT-5 nano (Minimal)OpenAIQuality Score 12.5Value Score 11.7