readable AI benchmarks (simplified)
OpenAI
GPT-6 Astra (xhigh)
GPT-6 Astra (xhigh) has a Quality Score of 78.2, ranking 6th among 284 scored models. Per 1M tokens, pricing is $10.00 input, $50.00 output, $1.00 cached input, and $12.50 cached output. It accepts text and image input, outputs text, and has a 1M token context window. Its Reliability Score is 71.7, ranking 3rd among 284 scored models, above average (total average: 35.4). Its Value Score is 43.9, high compared with the total Value average of 29.1.
Quality Score78.2coverage 94.7%: missing CursorBench 3.2 and DeepSWE v1.1
Value Score43.9
Reliability71.7
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
- $10.00
- Output
- $50.00
- Cached Input
- $1.00
- Cached Output
- $12.50
- Cost per task
- $1.20
Capability
- Intelligence
- 61.0
- Coding
- 75.9
- Agentic
- 51.3
- Omniscience
- 43.4
- Correct
- 61.9%
- Blended price
- $7.70
Answer outcomes
Attempt rate: 80.3%
Correct 61.9%Incorrect 18.4%Abstained 19.7%
Artificial Analysis benchmarks
- GDPval-AA v2
- 55%
- τ³-Banking
- 43%
- Terminal-Bench v2.1
- 89%
- SciCode
- 50%
- Humanity’s Last Exam
- 55%
- GPQA Diamond
- 96%
- CritPt
- 31%
- AA-Omniscience
- 72%
- AA-LCR
- 74%
Similar models
- GPT-6 Astra (max)OpenAIQuality Score 78.5Value Score 44.2
- GPT-6 Astra (high)OpenAIQuality Score 77.7Value Score 43.5
- GPT-6 Astra (medium)OpenAIQuality Score 76.5Value Score 42.7
- GPT-5.6 Sol (max)OpenAIQuality Score 74.1Value Score 47.1
- GPT-6 Astra (low)OpenAIQuality Score 74.5Value Score 41.2
- GPT-5.6 Sol (xhigh)OpenAIQuality Score 72.5Value Score 45.8