readable AI benchmarks (simplified)
OpenAI
GPT-4o (Aug '24)
GPT-4o (Aug '24) has a Quality Score of 25.7, ranking 298th among 551 scored models. Per 1M tokens, pricing is $2.50 input, $10.00 output, and $1.25 cached input. It accepts text and image input, outputs text, and has a 128k token context window. Its Reliability Score is 39.6, ranking 221st among 553 scored models, above average (total average: 35.6). Its Value Score is 16.2, low compared with the total Value average of 30.7.
Quality Score25.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score16.2
Factual reliability39.6
Cache Discount50%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 128k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $2.50
- Output
- $10.00
- Cached Input
- $1.25
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 7.7
- Coding
- not available
- Agentic
- not available
- Omniscience
- -20.9
- Correct
- 23.7%
- Blended price
- $2.38
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 68.3%
Correct 23.7%Incorrect 44.6%Partial / not attempted 31.7%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 2%
- GPQA Diamond
- 52%
- CritPt
- 0%
- AA-Omniscience
- 40%
- AA-LCR
- 41%
Similar models
- GPT-5 (minimal)OpenAIQuality Score 25.4Value Score 17.1
- GPT-5.4 nano (Non-Reasoning)OpenAIQuality Score 24.6Value Score 21.0
- GPT-4o (Nov '24)OpenAIQuality Score 28.9Value Score 18.1
- GPT-4.1OpenAIQuality Score 24.9Value Score 16.5
- GPT-5.1 (Non-reasoning)OpenAIQuality Score 26.6Value Score 18.0
- GPT-4OpenAIQuality Score 21.7Value Score not available