OpenAI
GPT-5.6 Terra (low)
Quality Score51.0
Value Score34.4
Reliability46.6
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
- $2.00
- Output
- $12.00
- Cached Input
- $0.200
- Cached Output
- $2.50
- Cost per task
- $0.094
Capability
- Intelligence
- 41.3
- Coding
- 58.1
- Agentic
- 31.5
- Omniscience
- -6.8
- Correct
- 43.7%
- Blended price
- $1.74
Answer outcomes
Correct 43.7%Incorrect 50.6%Abstained 5.7%
Artificial Analysis benchmarks
- GDPval-AA v2
- 38%
- τ³-Banking
- 19%
- Terminal-Bench v2.1
- 63%
- SciCode
- 49%
- Humanity’s Last Exam
- 29%
- GPQA Diamond
- 84%
- CritPt
- 9%
- AA-Omniscience
- 47%
- AA-LCR
- 69%
Similar models
- GPT-5.6 Luna (high)OpenAIQuality Score 52.8Value Score 48.6
- GPT-5.6 Luna (medium)OpenAIQuality Score 46.4Value Score 42.0
- GPT-5.6 Terra (medium)OpenAIQuality Score 55.6Value Score 37.9
- GPT-5.6 Luna (xhigh)OpenAIQuality Score 55.6Value Score 51.3
- GPT-5.3 Codex (xhigh)OpenAIQuality Score 58.6Value Score 39.0
- GPT-5.6 Terra (high)OpenAIQuality Score 58.6Value Score 40.1