OpenAI
GPT-5.6 Sol (max)
Quality Score74.5
Value Score45.2
Reliability61.0
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $5.00
- Output
- $30.00
- Cached Input
- $0.500
- Cached Output
- $6.25
- Cost per task
- $1.23
Capability
- Intelligence
- 60.9
- Coding
- 77.4
- Agentic
- 57.8
- Omniscience
- 22.0
- Correct
- 59.4%
- Blended price
- $4.35
Answer outcomes
Correct 59.4%Incorrect 37.4%Abstained 3.2%
Artificial Analysis benchmarks
- GDPval-AA v2
- 61%
- τ³-Banking
- 44%
- Terminal-Bench v2.1
- 88%
- SciCode
- 56%
- Humanity’s Last Exam
- 49%
- GPQA Diamond
- 94%
- CritPt
- 32%
- AA-Omniscience
- 61%
- AA-LCR
- 78%
Similar models
- GPT-5.6 Sol (xhigh)OpenAIQuality Score 73.0Value Score 44.1
- GPT-5.6 Sol (high)OpenAIQuality Score 71.5Value Score 43.1
- GPT-5.6 Sol (medium)OpenAIQuality Score 70.1Value Score 42.0
- GPT-5.6 Terra (max)OpenAIQuality Score 64.6Value Score 44.4
- GPT-5.6 Sol (low)OpenAIQuality Score 66.4Value Score 39.2
- GPT-5.6 Terra (xhigh)OpenAIQuality Score 60.6Value Score 41.8