OpenAI
o3
Quality Score38.8
Value Score27.3
Reliability42.2
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
- $2.00
- Output
- $8.00
- Cached Input
- $0.500
- Cached Output
- not available
- Cost per task
- not available
Capability
- Intelligence
- 31.1
- Coding
- not available
- Agentic
- not available
- Omniscience
- -15.6
- Correct
- 38.6%
- Blended price
- $1.55
Answer outcomes
Correct 38.6%Incorrect 54.1%Abstained 7.3%
Artificial Analysis benchmarks
- SciCode
- 41%
- Humanity’s Last Exam
- 20%
- GPQA Diamond
- 83%
- CritPt
- 1%
- AA-Omniscience
- 42%
- AA-LCR
- 73%
Similar models
- GPT-5.6 Luna (low)OpenAIQuality Score 42.2Value Score 37.7
- GPT-5.5 Instant (June 2026)OpenAIQuality Score 44.5Value Score 24.8
- GPT-5.6 Luna (medium)OpenAIQuality Score 46.4Value Score 42.0
- GPT-5.6 Terra (low)OpenAIQuality Score 51.0Value Score 34.4
- gpt-oss-120b (high)OpenAIQuality Score 22.4Value Score 24.3
- GPT-5.6 Luna (high)OpenAIQuality Score 52.8Value Score 48.6