readable AI benchmarks (simplified)
OpenAI
o4-mini (high)
o4-mini (high) has a Quality Score of 28.9, ranking 258th among 551 scored models. Per 1M tokens, pricing is $1.10 input, $4.40 output, and $0.275 cached input. It accepts text and image input, outputs text, and has a 200k token context window. Its Reliability Score is 32.1, ranking 285th among 553 scored models, below average (total average: 35.6). Its Value Score is 20.6, low compared with the total Value average of 30.7.
Quality Score28.9coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score20.6
Factual reliability32.1
Cache Discount75%
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 200k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $1.10
- Output
- $4.40
- Cached Input
- $0.275
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 16.7
- Coding
- not available
- Agentic
- not available
- Omniscience
- -35.7
- Correct
- 24.8%
- Blended price
- $0.853
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 85.3%
Correct 24.8%Incorrect 60.5%Partial / not attempted 14.7%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 17%
- GPQA Diamond
- 78%
- CritPt
- 1%
- AA-Omniscience
- 32%
- AA-LCR
- 61%
Similar models
- GPT-5 nano (medium)OpenAIQuality Score 28.2Value Score 26.3
- GPT-5 nano (high)OpenAIQuality Score 27.8Value Score 26.0
- GPT-5 mini (high)OpenAIQuality Score 33.6Value Score 27.4
- o1OpenAIQuality Score 34.0Value Score 17.6
- GPT-5.4 nano (xhigh)OpenAIQuality Score 33.6Value Score 28.6
- GPT-5.4 mini (medium)OpenAIQuality Score 35.0Value Score 25.8