OpenAI
GPT-5.6 Terra (xhigh)
Quality Score60.6
Value Score41.8
Reliability48.5
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
- $0.305
Capability
- Intelligence
- 52.8
- Coding
- 70.6
- Agentic
- 46.5
- Omniscience
- -3.0
- Correct
- 45.5%
- Blended price
- $1.74
Answer outcomes
Correct 45.5%Incorrect 48.5%Abstained 6.0%
Artificial Analysis benchmarks
- GDPval-AA v2
- 54%
- τ³-Banking
- 30%
- Terminal-Bench v2.1
- 80%
- SciCode
- 52%
- Humanity’s Last Exam
- 42%
- GPQA Diamond
- 91%
- CritPt
- 27%
- AA-Omniscience
- 49%
- AA-LCR
- 75%
Similar models
- GPT-5.6 Luna (max)OpenAIQuality Score 57.3Value Score 53.2
- GPT-5.6 Terra (high)OpenAIQuality Score 58.6Value Score 40.1
- GPT-5.6 Terra (max)OpenAIQuality Score 64.6Value Score 44.4
- GPT-5.3 Codex (xhigh)OpenAIQuality Score 58.6Value Score 39.0
- GPT-5.6 Luna (xhigh)OpenAIQuality Score 55.6Value Score 51.3
- GPT-5.6 Sol (low)OpenAIQuality Score 66.4Value Score 39.2