readable AI benchmarks (simplified)
OpenAI
GPT-4
GPT-4 has a Quality Score of 21.7, ranking 351st among 551 scored models. Per 1M tokens, pricing is $30.00 input and $60.00 output. It accepts text input, outputs text, and has a 8,192 token context window. Its Reliability Score is 33.1, ranking 277th among 553 scored models, below average (total average: 35.6).
Quality Score21.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability33.1
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 8,192 tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $30.00
- Output
- $60.00
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 6.7
- Coding
- not available
- Agentic
- not available
- Omniscience
- -33.8
- Correct
- 21.0%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 75.8%
Correct 21.0%Incorrect 54.8%Partial / not attempted 24.2%
Artificial Analysis benchmarks
- GDPval-AA v2
- 0%
- GPQA Diamond
- 35%
- AA-Omniscience
- 33%
Similar models
- GPT-5.4 mini (Non-Reasoning)OpenAIQuality Score 22.2Value Score 16.4
- GPT-5 mini (minimal)OpenAIQuality Score 19.4Value Score 15.8
- GPT-4.1 miniOpenAIQuality Score 19.4Value Score 15.6
- GPT-4o (Aug '24)OpenAIQuality Score 25.7Value Score 16.2
- GPT-4.1 nanoOpenAIQuality Score 16.6Value Score 15.2
- GPT-5.4 nano (Non-Reasoning)OpenAIQuality Score 24.6Value Score 21.0